NeurIPS 2022 Schedule

Filter Events

MON 28 NOV

5 a.m.

Registration Desk

(ends 5:00 PM)

5:30 a.m.

Affinity Workshop:

Women in Machine Learning

(ends 11:00 AM)

6 a.m.

Affinity Workshop:

LatinX in AI

(ends 4:00 PM)

7 a.m.

Workshop:

Queer in AI

(ends 4:00 PM)

NewInML:

New In ML

(ends 3:30 PM)

7:30 a.m.

Expo Talk Panel:

TIPDAT: ML based Optimization Explainer

(ends 8:30 AM)

Expo Talk Panel:

End-to-end cloud-based Document Intelligence Architecture using the open-source Feathr Feature Store, the SynapseML Spark library, and Hugging Face Extractive Question Answering

(ends 8:30 AM)

Expo Workshop:

PyTorch: New advances for large-scale training and performance optimizations

(ends 10:30 AM)

Expo Workshop:

Graph Neural Networks in Tensorflow: A Practical Guide

(ends 10:25 AM)

Expo Workshop:

Fine-tuning stable diffusion models: massive creativity without massive bills

(ends 10:30 AM)

Expo Workshop:

Get ready, your Jupyter Notebook goes to production!

(ends 10:30 AM)

7:40 a.m.

Affinity Workshop:

Black in AI

(ends 4:00 PM)

8 a.m.

Expo Demonstration:

Practical Deployment of Secure Federated Learning: Challenges, Opportunities and Solutions

(duration 2.0 hr)

Expo Demonstration:

Real-time Navigation of Chemical Space with Cloud-Based Inference from MoLFormer

(duration 2.0 hr)

Expo Demonstration:

Full-Stack 3D Scene Understanding on an Extended Reality Headset

(duration 2.0 hr)

Expo Demonstration:

Conditional Compute for On-device Video Understanding

(duration 2.0 hr)

Expo Demonstration:

Efficient super-resolution using 4-bit integer quantization for real-time mobile applications

(duration 2.0 hr)

Expo Demonstration:

Human Modeling and Strategic Reasoning in the Game of Diplomacy

(duration 2.0 hr)

Expo Demonstration:

Software-Delivered AI: Using Sparse-Quantization for Fastest Inference on Deep Neural Networks

(duration 2.0 hr)

Expo Demonstration:

Build Better Models Faster with W&B

(duration 2.0 hr)

Mentorship:

Education Outreach

(ends 1:00 PM)

8:30 a.m.

Expo Talk Panel:

Machine Learning and Optimization for Automated Trading at HRT

(ends 9:30 AM)

Expo Talk Panel:

Challenges & Opportunities for Ethical AI in Practice

(ends 9:30 AM)

9 a.m.

Break:

Coffee Break

(ends 10:00 AM)

9:30 a.m.

Affinity Workshop:

Indigenous in AI

(ends 4:00 PM)

Expo Talk Panel:

Using AI for Reduced-Order Modeling

(ends 10:30 AM)

Expo Talk Panel:

Uncertainty quantification for fair and transparent AI-assisted decision-making

(ends 10:30 AM)

11 a.m.

Expo Talk Panel:

Understanding the Landscape of the latest Large Models - Virtual

(ends 12:00 PM)

noon

Expo Demonstration:

Practical Deployment of Secure Federated Learning: Challenges, Opportunities and Solutions

(duration 2.0 hr)

Expo Demonstration:

Real-time Navigation of Chemical Space with Cloud-Based Inference from MoLFormer

(duration 2.0 hr)

Expo Demonstration:

Full-Stack 3D Scene Understanding on an Extended Reality Headset

(duration 2.0 hr)

Expo Demonstration:

Conditional Compute for On-device Video Understanding

(duration 2.0 hr)

Expo Demonstration:

Efficient super-resolution using 4-bit integer quantization for real-time mobile applications

(duration 2.0 hr)

Expo Demonstration:

Human Modeling and Strategic Reasoning in the Game of Diplomacy

(duration 2.0 hr)

Expo Demonstration:

Software-Delivered AI: Using Sparse-Quantization for Fastest Inference on Deep Neural Networks

(duration 2.0 hr)

Expo Demonstration:

Build Better Models Faster with W&B

(duration 2.0 hr)

Expo Talk Panel:

Towards learning agents for solving complex real-world tasks

(ends 1:00 PM)

Expo Talk Panel:

Sparse annotation strategies at scale

(ends 1:00 PM)

Expo Workshop:

Intro to TensorFlow and JAX

(ends 3:00 PM)

Expo Workshop:

AutoGluon: Empowering (MultiModal) AutoML for the next 10 Million users

(ends 3:00 PM)

Expo Workshop:

Impactful graph neural networks via DGL: A Tale of Research and Productization

(ends 3:00 PM)

12:30 p.m.

Affinity Workshop:

Global South in AI

(ends 4:00 PM)

1 p.m.

Expo Talk Panel:

Generative Understanding of 3D Scenes

(ends 2:00 PM)

Expo Talk Panel:

Adapt and Optimize ML Models for Hardware-Aware AI

(ends 2:00 PM)

1:30 p.m.

Break:

Coffee Break

(ends 2:30 PM)

2 p.m.

Expo Talk Panel:

Integrating modern machine learning and single cell technologies into drug target discovery - lessons from the frontline.

(ends 3:00 PM)

Expo Talk Panel:

Human-in-the-Loop Is Here to Stay

(ends 3:00 PM)

2:30 p.m.

Affinity Workshop:

North Africans in ML

(ends 4:00 PM)

Affinity Poster Session:

Affinity Poster Session

(ends 4:00 PM)

3 p.m.

Remarks:

Opening Remarks

(ends 3:15 PM)

3:15 p.m.

Invited Talk:

Could a Large Language Model be Conscious?

David Chalmers

(ends 4:00 PM)

4 p.m.

Reception:

Reception

(ends 6:00 PM)

TUE 29 NOV

5 a.m.

Registration Desk

(ends 4:00 PM)

7:30 a.m.

Invited Talk:

Algorithms On the Bench: Examining Validity of ML Systems in the Public Sphere

Rediet Abebe

(ends 8:30 AM)

8:30 a.m.

Break:

Coffee Break

(ends 9:00 AM)

9 a.m.

Poster Session 1 [9:00-11:00]

Efficient Change-Point Detection for Tackling Piecewise-Stationary Bandits

A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking

FedPop: A Bayesian Approach for Personalised Federated Learning

Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach

Functional Ensemble Distillation

Improving Zero-Shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions

Differentially Private Model Compression

Self-explaining deep models with logic rule reasoning

AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints

Behavior Transformers: Cloning $k$ modes with one stone

Equivariant Networks for Zero-Shot Coordination

Bandit Theory and Thompson Sampling-Guided Directed Evolution for Sequence Optimization

What You See is What You Classify: Black Box Attributions

Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation

Tree ensemble kernels for Bayesian optimization with known constraints over mixed-feature spaces

Sparse Fourier Backpropagation in Cryo-EM Reconstruction

Predictive Querying for Autoregressive Neural Sequence Models

Extracting computational mechanisms from neural data using low-rank RNNs

Modeling the Machine Learning Multiverse

AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuning

Retrospective Adversarial Replay for Continual Learning

Learning Neural Set Functions Under the Optimal Subset Oracle

Efficient Architecture Search for Diverse Tasks

When Do Flat Minima Optimizers Work?

The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes

LTMD: Learning Improvement of Spiking Neural Networks with Learnable Thresholding Neurons and Moderate Dropout

Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation

UMIX: Improving Importance Weighting for Subpopulation Shift via Uncertainty-Aware Mixup

Scalable Multi-agent Covering Option Discovery based on Kronecker Graphs

PaCo: Parameter-Compositional Multi-task Reinforcement Learning

ConfounderGAN: Protecting Image Data Privacy with Causal Confounder

Mask-based Latent Reconstruction for Reinforcement Learning

Improved Fine-Tuning by Better Leveraging Pre-Training Data

Redundancy-Free Message Passing for Graph Neural Networks

Towards Improving Faithfulness in Abstractive Summarization

Delving into Out-of-Distribution Detection with Vision-Language Representations

CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning

Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training

EfficientFormer: Vision Transformers at MobileNet Speed

VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

Large-batch Optimization for Dense Visual Predictions: Training Faster R-CNN in 4.2 Minutes

Semi-Supervised Video Salient Object Detection Based on Uncertainty-Guided Pseudo Labels

UniCLIP: Unified Framework for Contrastive Language-Image Pre-training

Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields

Learning Consistency-Aware Unsigned Distance Functions Progressively from Raw Point Clouds

Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty

Okapi: Generalising Better by Making Statistical Matches Match

Revisiting Sparse Convolutional Model for Visual Recognition

Random Normalization Aggregation for Adversarial Defense

Batch Multi-Fidelity Active Learning with Budget Constraints

Scalable and Efficient Training of Large Convolutional Neural Networks with Differential Privacy

Factuality Enhanced Language Models for Open-Ended Text Generation

Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering

A Closer Look at Weakly-Supervised Audio-Visual Source Localization

GlanceNets: Interpretable, Leak-proof Concept-based Models

AgraSSt: Approximate Graph Stein Statistics for Interpretable Assessment of Implicit Graph Generators

No Free Lunch from Deep Learning in Neuroscience: A Case Study through Models of the Entorhinal-Hippocampal Circuit

Inherently Explainable Reinforcement Learning in Natural Language

EZNAS: Evolving Zero-Cost Proxies For Neural Architecture Scoring

Uncertainty Estimation Using Riemannian Model Dynamics for Offline Reinforcement Learning

Structured Energy Network As a Loss

The Minority Matters: A Diversity-Promoting Collaborative Metric Learning Algorithm

Sharpness-Aware Training for Free

Interpreting Operation Selection in Differentiable Architecture Search: A Perspective from Influence-Directed Explanations

Scalable design of Error-Correcting Output Codes using Discrete Optimization with Graph Coloring

Amortized Mixing Coupling Processes for Clustering

GraphQNTK: Quantum Neural Tangent Kernel for Graph Data

ShuffleMixer: An Efficient ConvNet for Image Super-Resolution

Quo Vadis: Is Trajectory Forecasting the Key Towards Long-Term Multi-Object Tracking?

Adapting Self-Supervised Vision Transformers by Probing Attention-Conditioned Masking Consistency

Learning Latent Seasonal-Trend Representations for Time Series Forecasting

Pluralistic Image Completion with Gaussian Mixture Models

CoupAlign: Coupling Word-Pixel with Sentence-Mask Alignments for Referring Image Segmentation

Make an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis

Graph Few-shot Learning with Task-specific Structures

Co-Modality Graph Contrastive Learning for Imbalanced Node Classification

Recommender Forest for Efficient Retrieval

Label Noise in Adversarial Training: A Novel Perspective to Study Robust Overfitting

Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks

SemiFL: Semi-Supervised Federated Learning for Unlabeled Clients with Alternate Training

Task-Agnostic Graph Explanations

CageNeRF: Cage-based Neural Radiance Field for Generalized 3D Deformation and Animation

LECO: Learnable Episodic Count for Task-Specific Intrinsic Reward

Resource-Adaptive Federated Learning with All-In-One Neural Composition

Block-Recurrent Transformers

Distinguishing Learning Rules with Brain Machine Interfaces

Imitating Past Successes can be Very Suboptimal

Bounded-Regret MPC via Perturbation Analysis: Prediction Error, Constraints, and Nonlinearity

Neural Conservation Laws: A Divergence-Free Perspective

Relaxing Equivariance Constraints with Non-stationary Continuous Filters

Continual Learning In Environments With Polynomial Mixing Times

Non-Linear Coordination Graphs

Rate-Distortion Theoretic Bounds on Generalization Error for Distributed Learning

Mirror Descent Maximizes Generalized Margin and Can Be Implemented Efficiently

Instance-Dependent Near-Optimal Policy Identification in Linear MDPs via Online Experiment Design

On the Complexity of Adversarial Decision Making

Convergence beyond the over-parameterized regime using Rayleigh quotients

An Algorithm for Learning Switched Linear Dynamics from Data

Differentially Private Learning Needs Hidden State (Or Much Faster Convergence)

Cluster Randomized Designs for One-Sided Bipartite Experiments

Near-Optimal Randomized Exploration for Tabular Markov Decision Processes

Order-Invariant Cardinality Estimators Are Differentially Private

Mirror Descent with Relative Smoothness in Measure Spaces, with application to Sinkhorn and EM

Generalization Error Bounds on Deep Learning with Markov Datasets

Autoinverse: Uncertainty Aware Inversion of Neural Networks

Optimal Transport of Classifiers to Fairness

Path Independent Equilibrium Models Can Better Exploit Test-Time Computation

Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting

On Sample Optimality in Personalized Collaborative and Federated Learning

Active Ranking without Strong Stochastic Transitivity

How Sampling Impacts the Robustness of Stochastic Neural Networks

Convexity Certificates from Hessians

Optimal Binary Classification Beyond Accuracy

Sample Constrained Treatment Effect Estimation

Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss

SecureFedYJ: a safe feature Gaussianization protocol for Federated Learning

Continual learning: a feature extraction formalization, an efficient algorithm, and fundamental obstructions

Evolution of Neural Tangent Kernels under Benign and Adversarial Training

Parameters or Privacy: A Provable Tradeoff Between Overparameterization and Membership Inference

Active Exploration for Inverse Reinforcement Learning

A Unified Framework for Deep Symbolic Regression

Learning Generalized Policy Automata for Relational Stochastic Shortest Path Problems

CARD: Classification and Regression Diffusion Models

GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networks

So3krates: Equivariant attention for interactions on arbitrary length-scales in molecular systems

Micro and Macro Level Graph Modeling for Graph Variational Auto-Encoders

Learning Representations via a Robust Behavioral Metric for Deep Reinforcement Learning

Transferring Fairness under Distribution Shifts via Fair Consistency Regularization

Bridging the Gap from Asymmetry Tricks to Decorrelation Principles in Non-contrastive Self-supervised Learning

Template based Graph Neural Network with Optimal Transport Distances

A composable machine-learning approach for steady-state simulations on high-resolution grids

SoteriaFL: A Unified Framework for Private Federated Learning with Communication Compression

A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective

From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent

Stability and Generalization for Markov Chain Stochastic Gradient Methods

Learning Energy Networks with Generalized Fenchel-Young Losses

AZ-whiteness test: a test for signal uncorrelation on spatio-temporal graphs

Equivariant Networks for Crystal Structures

Text Classification with Born's Rule

A Probabilistic Graph Coupling View of Dimension Reduction

Laplacian Autoencoders for Learning Stochastic Representations

UQGAN: A Unified Model for Uncertainty Quantification of Deep Classifiers trained via Conditional GANs

Variational Model Perturbation for Source-Free Domain Adaptation

On the Effect of Pre-training for Transformer in Different Modality on Offline Reinforcement Learning

Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps

EcoFormer: Energy-Saving Attention with Linear Complexity

Dataset Distillation using Neural Feature Regression

Iterative Scene Graph Generation

ALIFE: Adaptive Logit Regularizer and Feature Replay for Incremental Semantic Segmentation

Hyperbolic Feature Augmentation via Distribution Estimation and Infinite Sampling on Manifolds

Provably Adversarially Robust Detection of Out-of-Distribution Data (Almost) for Free

Distributed Methods with Compressed Communication for Solving Variational Inequalities, with Theoretical Guarantees

Global Convergence and Stability of Stochastic Gradient Descent

Regret Bounds for Information-Directed Reinforcement Learning

Truncated Matrix Power Iteration for Differentiable DAG Learning

Error Analysis of Tensor-Train Cross Approximation

Efficient Risk-Averse Reinforcement Learning

Learning Robust Dynamics through Variational Sparse Gating

DiSC: Differential Spectral Clustering of Features

WeightedSHAP: analyzing and improving Shapley based feature attributions

Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures

On the Global Convergence Rates of Decentralized Softmax Gradient Play in Markov Potential Games

Safety Guarantees for Neural Network Dynamic Systems via Stochastic Barrier Functions

A Unified Framework for Alternating Offline Model Training and Policy Learning

Decentralized Local Stochastic Extra-Gradient for Variational Inequalities

Gradient Estimation with Discrete Stein Operators

On the SDEs and Scaling Rules for Adaptive Gradient Algorithms

Root Cause Analysis of Failures in Microservices through Causal Discovery

Low-rank Optimal Transport: Approximation, Statistics and Debiasing

Learning single-index models with shallow neural networks

Generalized Variational Inference in Function Spaces: Gaussian Measures meet Bayesian Deep Learning

Efficient identification of informative features in simulation-based inference

Exact learning dynamics of deep linear networks with prior knowledge

Adversarial training for high-stakes reliability

NaturalProver: Grounded Mathematical Proof Generation with Language Models

Open-Ended Reinforcement Learning with Neural Reward Functions

Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs

Memory safe computations with XLA compiler

C2FAR: Coarse-to-Fine Autoregressive Networks for Precise Probabilistic Forecasting

Continuous MDP Homomorphisms and Homomorphic Policy Gradient

Data augmentation for efficient learning from parametric experts

Generating Training Data with Language Models: Towards Zero-Shot Language Understanding

Deep Surrogate Assisted Generation of Environments

SGAM: Building a Virtual 3D World through Simultaneous Generation and Mapping

Evaluating Latent Space Robustness and Uncertainty of EEG-ML Models under Realistic Distribution Shifts

Predicting Cellular Responses to Novel Drug Perturbations at a Single-Cell Resolution

Fine-tuning language models to find agreement among humans with diverse preferences

A Unified Sequence Interface for Vision Tasks

Learning Probabilistic Models from Generator Latent Spaces with Hat EBM

Deep Generalized Schrödinger Bridge

NSNet: A General Neural Probabilistic Framework for Satisfiability Problems

Distributionally Robust Optimization with Data Geometry

Quantifying Statistical Significance of Neural Network-based Image Segmentation by Selective Inference

On Efficient Online Imitation Learning via Classification

Group Meritocratic Fairness in Linear Contextual Bandits

Subspace Recovery from Heterogeneous Data with Non-isotropic Noise

Knowledge Distillation: Bad Models Can Be Good Role Models

Active Labeling: Streaming Stochastic Gradients

Renyi Differential Privacy of Propose-Test-Release and Applications to Private and Robust Machine Learning

Stability and Generalization of Kernel Clustering: from Single Kernel to Multiple Kernel

Near-Optimal No-Regret Learning Dynamics for General Convex Games

Constrained Stochastic Nonconvex Optimization with State-dependent Markov Data

A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Bandits

Global Convergence of Federated Learning for Mixed Regression

Kernel similarity matching with Hebbian networks

Improved techniques for deterministic l2 robustness

Matryoshka Representation Learning

Ask4Help: Learning to Leverage an Expert for Embodied Tasks

Wavelet Feature Maps Compression for Image-to-Image CNNs

Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF

Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization

Semantic Diffusion Network for Semantic Segmentation

Non-Linguistic Supervision for Contrastive Learning of Sentence Embeddings

CUP: Critic-Guided Policy Reuse

XTC: Extreme Compression for Pre-trained Transformers Made Simple and Efficient

ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning

Distilling Representations from GAN Generator via Squeeze and Span

SHINE: SubHypergraph Inductive Neural nEtwork

Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer

Museformer: Transformer with Fine- and Coarse-Grained Attention for Music Generation

LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language Model

LION: Latent Point Diffusion Models for 3D Shape Generation

Learning low-dimensional generalizable natural features from retina using a U-net

Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples

The Pitfalls of Regularization in Off-Policy TD Learning

Fine-tuning Language Models over Slow Networks using Activation Quantization with Guarantees

Online Training Through Time for Spiking Neural Networks

General Cutting Planes for Bound-Propagation-Based Neural Network Verification

Universality of Group Convolutional Neural Networks Based on Ridgelet Analysis on Groups

Single Loop Gaussian Homotopy Method for Non-convex Optimization

Bring Your Own Algorithm for Optimal Differentially Private Stochastic Minimax Optimization

Multi-agent Performative Prediction with Greedy Deployment and Consensus Seeking Agents

A Multilabel Classification Framework for Approximate Nearest Neighbor Search

Spectral Bias in Practice: The Role of Function Frequency in Generalization

Influencing Long-Term Behavior in Multiagent Reinforcement Learning

Quality Not Quantity: On the Interaction between Dataset Design and Robustness of CLIP

Giving Feedback on Interactive Student Programs with Meta-Exploration

Unsupervised Object Representation Learning using Translation and Rotation Group Equivariant VAE

Few-Shot Continual Active Learning by a Robot

Data-Efficient Pipeline for Offline Reinforcement Learning with Limited Data

VoiceBlock: Privacy through Real-Time Adversarial Attacks with Audio-to-Audio Models

Retrieval-Augmented Diffusion Models

On Analyzing Generative and Denoising Capabilities of Diffusion-based Deep Generative Models

Toward Robust Spiking Neural Network Against Adversarial Perturbation

Debiased Causal Tree: Heterogeneous Treatment Effects Estimation with Unmeasured Confounding

On the Convergence of Stochastic Multi-Objective Gradient Manipulation and Beyond

Video-based Human-Object Interaction Detection from Tubelet Tokens

OTKGE: Multi-modal Knowledge Graph Embeddings via Optimal Transport

Hierarchical Lattice Layer for Partially Monotone Neural Networks

On the symmetries of the synchronization problem in Cryo-EM: Multi-Frequency Vector Diffusion Maps on the Projective Plane

What Makes a "Good" Data Augmentation in Knowledge Distillation - A Statistical Perspective

HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions

Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query Attacks

Revisiting Non-Parametric Matching Cost Volumes for Robust and Generalizable Stereo Matching

Learning Contrastive Embedding in Low-Dimensional Space

Few-Shot Fast-Adaptive Anomaly Detection

Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees

Exploration via Planning for Information about the Optimal Trajectory

Theoretical analysis of deep neural networks for temporally dependent observations

Provably sample-efficient RL with side information about latent dynamics

In What Ways Are Deep Neural Networks Invariant and How Should We Measure This?

Truncated proposals for scalable and hassle-free simulation-based inference

Calibrated Data-Dependent Constraints with Exact Satisfaction Guarantees

Policy Optimization with Linear Temporal Logic Constraints

Fast Instrument Learning with Faster Rates

Outlier-Robust Sparse Estimation via Non-Convex Optimization

Gradient Methods Provably Converge to Non-Robust Networks

Operator Splitting Value Iteration

Bayesian Optimistic Optimization: Optimistic Exploration for Model-based Reinforcement Learning

Learning from Stochastically Revealed Preference

Augmented RBMLE-UCB Approach for Adaptive Control of Linear Quadratic Systems

An $\alpha$-No-Regret Algorithm For Graphical Bilinear Bandits

Outlier-Robust Sparse Mean Estimation for Heavy-Tailed Distributions

Distributed Inverse Constrained Reinforcement Learning for Multi-agent Systems

Uplifting Bandits

Poisson Flow Generative Models

Multi-agent Dynamic Algorithm Configuration

Muffliato: Peer-to-Peer Privacy Amplification for Decentralized Optimization and Averaging

A Theory of PAC Learnability under Transformation Invariances

Lost in Latent Space: Examining failures of disentangled models at combinatorial generalisation

Biologically plausible solutions for spiking networks with efficient coding

Phase transitions in when feedback is useful

Simple and Optimal Greedy Online Contention Resolution Schemes

Private Estimation with Public Data

Robustness to Label Noise Depends on the Shape of the Noise Distribution

A general approximation lower bound in $L^p$ norm, with applications to feed-forward neural networks

Minimax Optimal Algorithms for Fixed-Budget Best Arm Identification

Minimax Optimal Online Imitation Learning via Replay Estimation

Approximate Euclidean lengths and distances beyond Johnson-Lindenstrauss

List-Decodable Sparse Mean Estimation

Finite-Time Last-Iterate Convergence for Learning in Multi-Player Games

SAGDA: Achieving $\mathcal{O}(\epsilon^{-2})$ Communication Complexity in Federated Min-Max Learning

Depth is More Powerful than Width with Prediction Concatenation in Deep Forest

Neural Abstractions

Random Rank: The One and Only Strategyproof and Proportionally Fair Randomized Facility Location Mechanism

Smooth Fictitious Play in Stochastic Games with Perturbed Payoffs and Unknown Transitions

The Query Complexity of Cake Cutting

Learning (Very) Simple Generative Models Is Hard

Cryptographic Hardness of Learning Halfspaces with Massart Noise

Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Functions

Accelerated Primal-Dual Gradient Method for Smooth and Convex-Concave Saddle-Point Problems with Bilinear Coupling

Sample-Efficient Learning of Correlated Equilibria in Extensive-Form Games

SAPD+: An Accelerated Stochastic Method for Nonconvex-Concave Minimax Problems

On Optimal Learning Under Targeted Data Poisoning

Taming Fat-Tailed (“Heavier-Tailed” with Potentially Infinite Variance) Noise in Federated Learning

Nearly Optimal Best-of-Both-Worlds Algorithms for Online Learning with Feedback Graphs

Better Best of Both Worlds Bounds for Bandits with Switching Costs

Coreset for Line-Sets Clustering

On the Efficient Implementation of High Accuracy Optimality of Profile Maximum Likelihood

Society of Agents: Regret Bounds of Concurrent Thompson Sampling

Improved Convergence Rate of Stochastic Gradient Langevin Dynamics with Variance Reduction and its Application to Optimization

Kernel Multimodal Continuous Attention

Empirical Gateaux Derivatives for Causal Inference

Bayesian Persuasion for Algorithmic Recourse

Hardness of Noise-Free Learning for Two-Hidden-Layer Neural Networks

The Hessian Screening Rule

Distributed Optimization for Overparameterized Problems: Achieving Optimal Dimension Independent Communication Complexity

Will Bilevel Optimizers Benefit from Loops

Expected Improvement for Contextual Bandits

Fast Neural Kernel Embeddings for General Activations

Maximum Common Subgraph Guided Graph Retrieval: Late and Early Interaction Networks

Hierarchical Agglomerative Graph Clustering in Poly-Logarithmic Depth

Understanding Deep Contrastive Learning via Coordinate-wise Optimization

Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning

Sparse Hypergraph Community Detection Thresholds in Stochastic Block Model

Don't Pour Cereal into Coffee: Differentiable Temporal Logic for Temporal Action Segmentation

Towards Versatile Embodied Navigation

CASA: Category-agnostic Skeletal Animal Reconstruction

Counterfactual Neural Temporal Point Process for Estimating Causal Influence of Misinformation on Social Media

Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling

Brain Network Transformer

Policy Optimization with Advantage Regularization for Long-Term Fairness in Decision Systems

SizeShiftReg: a Regularization Method for Improving Size-Generalization in Graph Neural Networks

The Phenomenon of Policy Churn

Learning to Find Proofs and Theorems by Learning to Refine Search Strategies: The Case of Loop Invariant Synthesis

Censored Quantile Regression Neural Networks for Distribution-Free Survival Analysis

Certifying Robust Graph Classification under Orthogonal Gromov-Wasserstein Threats

To update or not to update? Neurons at equilibrium in deep models

Improving Intrinsic Exploration with Language Abstractions

Masked Generative Adversarial Networks are Data-Efficient Generation Learners

Dance of SNN and ANN: Solving binding problem by combining spike timing and reconstructive attention

Theseus: A Library for Differentiable Nonlinear Optimization

Distributed Influence-Augmented Local Simulators for Parallel MARL in Large Networked Systems

Synthetic Model Combination: An Instance-wise Approach to Unsupervised Ensemble Learning

S4ND: Modeling Images and Videos as Multidimensional Signals with State Spaces

Decoupling Features in Hierarchical Propagation for Video Object Segmentation

Is Out-of-Distribution Detection Learnable?

QUARK: Controllable Text Generation with Reinforced Unlearning

Dynamics of SGD with Stochastic Polyak Stepsizes: Truly Adaptive Variants and Convergence to Exact Solution

Homomorphic Matrix Completion

Practical Adversarial Attacks on Spatiotemporal Traffic Forecasting Models

Characterizing the Ventral Visual Stream with Response-Optimized Neural Encoding Models

GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images

What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods

CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders

VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives

Accelerated Training of Physics-Informed Neural Networks (PINNs) using Meshless Discretizations

On the Importance of Gradient Norm in PAC-Bayesian Bounds

Temporally Disentangled Representation Learning

Natural gradient enables fast sampling in spiking neural networks

Triangulation candidates for Bayesian optimization

Near-Isometric Properties of Kronecker-Structured Random Tensor Embeddings

A permutation-free kernel two-sample test

Exponential Family Model-Based Reinforcement Learning via Score Matching

Learning with little mixing

Collaborative Linear Bandits with Adversarial Agents: Near-Optimal Regret Bounds

Communication Efficient Federated Learning for Generalized Linear Bandits

On Scrambling Phenomena for Randomly Initialized Recurrent Networks

Exponentially Improving the Complexity of Simulating the Weisfeiler-Lehman Test with Graph Neural Networks

Last-Iterate Convergence of Optimistic Gradient Method for Monotone Variational Inequalities

3DB: A Framework for Debugging Computer Vision Models

Unifying and Boosting Gradient-Based Training-Free Neural Architecture Search

Measuring Data Reconstruction Defenses in Collaborative Inference Systems

Function Classes for Identifiable Nonlinear Independent Component Analysis

Towards Disentangling Information Paths with Coded ResNeXt

Why do We Need Large Batchsizes in Contrastive Learning? A Gradient-Bias Perspective

On Robust Multiclass Learnability

Generalised Mutual Information for Discriminative Clustering

A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning

Anytime-Valid Inference For Multinomial Count Data

OpenOOD: Benchmarking Generalized Out-of-Distribution Detection

FinRL-Meta: Market Environments and Benchmarks for Data-Driven Financial Reinforcement Learning

NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Tasks

ETAB: A Benchmark Suite for Visual Representation Learning in Echocardiography

Turning the Tables: Biased, Imbalanced, Dynamic Tabular Datasets for ML Evaluation

How Well Do Unsupervised Learning Algorithms Model Human Real-time and Life-long Learning?

ActionSense: A Multimodal Dataset and Recording Framework for Human Activities Using Wearable Sensors in a Kitchen Environment

Breaking Bad: A Dataset for Geometric Fracture and Reassembly

FlyView: a bio-informed optical flow truth dataset for visual navigation using panoramic stereo vision

Chartalist: Labeled Graph Datasets for UTXO and Account-based Blockchains

SMPL: Simulated Industrial Manufacturing and Process Control Learning Environments

WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models

MTNeuro: A Benchmark for Evaluating Representations of Brain Structure Across Multiple Levels of Abstraction

xView3-SAR: Detecting Dark Fishing Activity Using Synthetic Aperture Radar Imagery

CEDe: A collection of expert-curated datasets with atom-level entity annotations for Optical Chemical Structure Recognition

FETA: Towards Specializing Foundational Models for Expert Task Applications

CAESAR: An Embodied Simulator for Generating Multimodal Referring Expression Datasets

Evaluating Out-of-Distribution Performance on Document Image Classifiers

Learning Long-Term Crop Management Strategies with CyclesGym

pFL-Bench: A Comprehensive Benchmark for Personalized Federated Learning

Myriad: a real-world testbed to bridge trajectory optimization and deep learning

Deep Limits and a Cut-Off Phenomenon for Neural Networks

Non-asymptotic and Accurate Learning of Nonlinear Dynamical Systems

Robust and scalable manifold learning via landmark diffusion for long-term medical signal processing

The Importance of Being Correlated: Implications of Dependence in Joint Spectral Inference across Multiple Networks

Foolish Crowds Support Benign Overfitting

[Re] Exacerbating Algorithmic Bias through Fairness Attacks

[Re] Replication Study of "Fairness and Bias in Online Selection"

[Re] Reproduction Study of Variational Fair Clustering

(ends 11:00 AM)

12:30 p.m.

Invited Talk:

Conformal Prediction in 2022

Emmanuel Candes

(ends 1:30 PM)

1:30 p.m.

Break:

Coffee Break

(ends 2:00 PM)

2 p.m.

Poster Session 2 [2:00-4:00]

A Nonconvex Framework for Structured Dynamic Covariance Recovery

Alignment-guided Temporal Attention for Video Action Recognition

TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels

On Feature Learning in the Presence of Spurious Correlations

Spatial Mixture-of-Experts

Exploring Length Generalization in Large Language Models

Neural Topological Ordering for Computation Graphs

Unsupervised Multi-View Object Segmentation Using Radiance Field Propagation

Offline Multi-Agent Reinforcement Learning with Knowledge Distillation

Enhanced Meta Reinforcement Learning via Demonstrations in Sparse Reward Environments

Maximum Class Separation as Inductive Bias in One Matrix

Training Uncertainty-Aware Classifiers with Conformalized Deep Learning

Efficiently Factorizing Boolean Matrices using Proximal Gradient Descent

FlowHMM: Flow-based continuous hidden Markov models

Merging Models with Fisher-Weighted Averaging

Holomorphic Equilibrium Propagation Computes Exact Gradients Through Finite Size Oscillations

Neural Payoff Machines: Predicting Fair and Stable Payoff Allocations Among Team Members

Additive MIL: Intrinsically Interpretable Multiple Instance Learning for Pathology

Making Look-Ahead Active Learning Strategies Feasible with Neural Tangent Kernels

Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse

Ordered Subgraph Aggregation Networks

Infinite Recommendation Networks: A Data-Centric Approach

Diversity vs. Recognizability: Human-like generalization in one-shot generative models

Geo-SIC: Learning Deformable Geometric Shapes in Deep Image Classifiers

Improving Transformer with an Admixture of Attention Heads

Preservation of the Global Knowledge by Not-True Distillation in Federated Learning

Information-Theoretic GAN Compression with Variational Energy-based Model

VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning

CLEAR: Generative Counterfactual Explanations on Graphs

Out-of-Distribution Detection with An Adaptive Likelihood Ratio on Informative Hierarchical VAE

Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation

A Coupled Design of Exploiting Record Similarity for Practical Vertical Federated Learning

ClimbQ: Class Imbalanced Quantization Enabling Robustness on Efficient Inferences

Public Wisdom Matters! Discourse-Aware Hyperbolic Fourier Co-Attention for Social Text Classification

SIREN: Shaping Representations for Detecting Out-of-Distribution Objects

Efficient and Effective Multi-task Grouping via Meta Learning on Task Combinations

DENSE: Data-Free One-Shot Federated Learning

SparCL: Sparse Continual Learning on the Edge

Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again

Multi-modal Grouping Network for Weakly-Supervised Audio-Visual Video Parsing

Searching for Better Spatio-temporal Alignment in Few-Shot Action Recognition

Learning Generalizable Part-based Feature Representation for 3D Point Clouds

Coordinates Are NOT Lonely - Codebook Prior Helps Implicit Neural 3D representations

Set-based Meta-Interpolation for Few-Task Meta-Learning

Zero-Shot Video Question Answering via Frozen Bidirectional Language Models

Masked Autoencoders As Spatiotemporal Learners

Uncovering the Structural Fairness in Graph Contrastive Learning

AutoMS: Automatic Model Selection for Novelty Detection with Error Rate Control

Learning Best Combination for Efficient N:M Sparsity

C-Mixup: Improving Generalization in Regression

GAPX: Generalized Autoregressive Paraphrase-Identification X

Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models

GAMA: Generative Adversarial Multi-Object Scene Attacks

Composite Feature Selection Using Deep Ensembles

Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods

Discovered Policy Optimisation

Learning Structure from the Ground up---Hierarchical Representation Learning by Chunking

Amortized Inference for Heterogeneous Reconstruction in Cryo-EM

Neural Approximation of Graph Topological Features

Towards Out-of-Distribution Sequential Event Prediction: A Causal Treatment

Improving Variational Autoencoders with Density Gap-based Regularization

End-to-end Stochastic Optimization with Energy-based Model

Physics-Embedded Neural Networks: Graph Neural PDE Solvers with Mixed Boundary Conditions

Advancing Model Pruning via Bi-level Optimization

Earthformer: Exploring Space-Time Transformers for Earth System Forecasting

Is Integer Arithmetic Enough for Deep Learning Training?

Dense Interspecies Face Embedding

Learning State-Aware Visual Representations from Audible Interactions

VITA: Video Instance Segmentation via Object Token Association

Graph Convolution Network based Recommender Systems: Learning Guarantee and Item Mixture Powered Strategy

Pyramid Attention For Source Code Summarization

An Empirical Study on Disentanglement of Negative-free Contrastive Learning

Cache-Augmented Inbatch Importance Resampling for Training Recommender Retriever

Draft-and-Revise: Effective Image Generation with Contextual RQ-Transformer

Get More at Once: Alternating Sparse Training with Gradient Correction

Uncertainty Estimation for Multi-view Data: The Power of Seeing the Whole Picture

Synergy-of-Experts: Collaborate to Improve Adversarial Robustness

Accelerating Certified Robustness Training via Knowledge Transfer

Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency

Self-supervised Amodal Video Object Segmentation

Rethinking Image Restoration for Object Detection

Unsupervised Learning of Shape Programs with Repeatable Implicit Parts

ELASTIC: Numerical Reasoning with Adaptive Symbolic Compiler

Learning dynamics of deep linear networks with multiple pathways

FP8 Quantization: The Power of the Exponent

Pushing the limits of fairness impossibility: Who's the fairest of them all?

Learning Dynamical Systems via Koopman Operator Regression in Reproducing Kernel Hilbert Spaces

Pseudo-Riemannian Graph Convolutional Networks

PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization

Learning Mixed Multinomial Logits with Provable Guarantees

Truly Deterministic Policy Optimization

A Consistent and Differentiable Lp Canonical Calibration Error Estimator

Frank-Wolfe-based Algorithms for Approximating Tyler's M-estimator

Reinforcement Learning with Logarithmic Regret and Policy Switches

Finite Sample Analysis Of Dynamic Regression Parameter Learning

Evaluating Robustness to Dataset Shift via Parametric Robustness Sets

Network change point localisation under local differential privacy

When Privacy Meets Partial Information: A Refined Analysis of Differentially Private Bandits

Diversified Recommendations for Agents with Adaptive Preferences

Confident Approximate Policy Iteration for Efficient Local Planning in $q^\pi$-realizable MDPs

Parameter-free Regret in High Probability with Heavy Tails

Shape And Structure Preserving Differential Privacy

Multi-layer State Evolution Under Random Convolutional Design

Graph Neural Networks with Adaptive Readouts

On the detrimental effect of invariances in the likelihood for variational inference

Causally motivated multi-shortcut identification and removal

Learning Predictions for Algorithms with Predictions

Near-Optimal Collaborative Learning in Bandits

Incentivizing Combinatorial Bandit Exploration

BR-SNIS: Bias Reduced Self-Normalized Importance Sampling

Differentially Private Learning with Margin Guarantees

Multiclass Learnability Beyond the PAC Framework: Universal Rates and Partial Concept Classes

Planning to the Information Horizon of BAMDPs via Epistemic State Abstraction

Pay attention to your loss : understanding misconceptions about Lipschitz neural networks

What You See is What You Get: Principled Deep Learning via Distributional Generalization

Data-Driven Offline Decision-Making via Invariant Representation Learning

Learning Manifold Dimensions with Conditional Variational Autoencoders

Asymptotics of $\ell_2$ Regularized Network Embeddings

TabNAS: Rejection Sampling for Neural Architecture Search on Tabular Datasets

Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations

CS-Shapley: Class-wise Shapley Values for Data Valuation in Classification

Teacher Forcing Recovers Reward Functions for Text Generation

Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure

MGNNI: Multiscale Graph Neural Networks with Implicit Layers

Gaussian Copula Embeddings

On Learning Fairness and Accuracy on Multiple Subgroups

Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning

Sequencer: Deep LSTM for Image Classification

Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts

Sound and Complete Verification of Polynomial Networks

DReS-FL: Dropout-Resilient Secure Federated Learning for Non-IID Clients via Secret Data Sharing

Generalized Laplacian Eigenmaps

Statistical, Robustness, and Computational Guarantees for Sliced Wasserstein Distances

Anchor-Changing Regularized Natural Policy Gradient for Multi-Objective Reinforcement Learning

RKHS-SHAP: Shapley Values for Kernel Methods

Temporally-Consistent Survival Analysis

ULNeF: Untangled Layered Neural Fields for Mix-and-Match Virtual Try-On

Diffusion-based Molecule Generation with Informative Prior Bridges

Learning with convolution and pooling operations in kernel methods

Optimizing Relevance Maps of Vision Transformers Improves Robustness

Unsupervised Causal Generative Understanding of Images

SelecMix: Debiased Learning by Contradicting-pair Sampling

Controllable Text Generation with Neurally-Decomposed Oracle

Explain My Surprise: Learning Efficient Long-Term Memory by predicting uncertain outcomes

Rethinking Resolution in the Context of Efficient Video Recognition

Unsupervised Visual Representation Learning via Mutual Information Regularized Assignment

Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning

Infinite-Fidelity Coregionalization for Physical Simulation

Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost

Private Set Generation with Discriminative Information

Private Synthetic Data for Multitask Learning and Marginal Queries

Deep Equilibrium Approaches to Diffusion Models

A Reparametrization-Invariant Sharpness Measure Based on Information Geometry

A Statistical Online Inference Approach in Averaged Stochastic Approximation

Understanding Square Loss in Training Overparametrized Neural Network Classifiers

A Deep Reinforcement Learning Framework for Column Generation

Monte Carlo Augmented Actor-Critic for Sparse Reward Deep Reinforcement Learning from Suboptimal Demonstrations

Models Out of Line: A Fourier Lens on Distribution Shift Robustness

Pre-Trained Language Models for Interactive Decision-Making

The Neural Testbed: Evaluating Joint Predictions

Is a Modular Architecture Enough?

A theory of weight distribution-constrained learning

Fast Bayesian Estimation of Point Process Intensity as Function of Covariates

PopArt: Efficient Sparse Regression and Experimental Design for Optimal Sparse Linear Bandits

Parallel Tempering With a Variational Reference

Embrace the Gap: VAEs Perform Independent Mechanism Analysis

Learning Deep Input-Output Stable Dynamics

Towards Reliable Simulation-Based Inference with Balanced Neural Ratio Estimation

Hyperbolic Embedding Inference for Structured Multi-Label Prediction

Surprising Instabilities in Training Deep Networks and a Theoretical Analysis

Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiation

Boosting the Performance of Generic Deep Neural Network Frameworks with Log-supermodular CRFs

SnAKe: Bayesian Optimization with Pathwise Exploration

On Measuring Excess Capacity in Neural Networks

Robust Reinforcement Learning using Offline Data

Thinned random measures for sparse graphs with overlapping communities

Value Function Decomposition for Iterative Design of Reinforcement Learning Agents

The Privacy Onion Effect: Memorization is Relative

Evaluating Graph Generative Models with Contrastively Learned Features

Weakly supervised causal representation learning

Kernel Memory Networks: A Unifying Framework for Memory Modeling

Wavelet Score-Based Generative Modeling

Monte Carlo Tree Descent for Black-Box Optimization

Adaptive Sampling for Discovery

Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data

Beyond Rewards: a Hierarchical Perspective on Offline Multiagent Behavioral Analysis

Deep Hierarchical Planning from Pixels

Private Multiparty Perception for Navigation

Mesoscopic modeling of hidden spiking neurons

Toward a realistic model of speech processing in the brain with self-supervised learning

Harmonizing the object recognition strategies of deep neural networks with humans

Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning

Efficient Training of Low-Curvature Neural Networks

Consistent Sufficient Explanations and Minimal Local Rules for explaining the decision of any classifier or regressor

Social-Inverse: Inverse Decision-making of Social Contagion Management with Task Migrations

Nonlinear Sufficient Dimension Reduction with a Stochastic Neural Network

Data-Driven Conditional Robust Optimization

Subgame Solving in Adversarial Team Games

Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions

Universal Rates for Interactive Learning

Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction

Learning from Label Proportions by Learning with Label Noise

Efficient Methods for Non-stationary Online Learning

Black-Box Generalization: Stability of Zeroth-Order Learning

Provably Efficient Offline Multi-agent Reinforcement Learning via Strategy-wise Bonus

Minimax-Optimal Multi-Agent RL in Markov Games With a Generative Model

Decentralized Gossip-Based Stochastic Bilevel Optimization over Communication Networks

VaiPhy: a Variational Inference Based Algorithm for Phylogeny

Local-Global MCMC kernels: the best of both worlds

Posterior Matching for Arbitrary Conditioning

FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting

LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models

Rare Gems: Finding Lottery Tickets at Initialization

Rethinking the compositionality of point clouds through regularization in the hyperbolic space

QC-StyleGAN - Quality Controllable Image Generation and Manipulation

Look Around and Refer: 2D Synthetic Semantics Knowledge Distillation for 3D Visual Grounding

Fine-Grained Semantically Aligned Vision-Language Pre-Training

Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition

Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning

SageMix: Saliency-Guided Mixup for Point Clouds

Local Spatiotemporal Representation Learning for Longitudinally-consistent Neuroimage Analysis

Decomposing NeRF for Editing via Feature Field Distillation

Dual-discriminative Graph Neural Network for Imbalanced Graph-level Anomaly Detection

Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving

Hierarchical Normalization for Robust Monocular Depth Estimation

GLIPv2: Unifying Localization and Vision-Language Understanding

AVLEN: Audio-Visual-Language Embodied Navigation in 3D Environments

Single-phase deep learning in cortico-cortical networks

Understanding Robust Learning through the Lens of Representation Similarities

EF-BV: A Unified Theory of Error Feedback and Variance Reduction Mechanisms for Biased and Unbiased Compression in Distributed Optimization

LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning

Scalable Neural Video Representations with Learnable Positional Features

Are All Losses Created Equal: A Neural Collapse Perspective

Lazy and Fast Greedy MAP Inference for Determinantal Point Process

Smoothed Online Convex Optimization Based on Discounted-Normal-Predictor

Privacy Induces Robustness: Information-Computation Gaps and Sparse Mean Estimation

Fast Bayesian Coresets via Subsampling and Quasi-Newton Refinement

Biological Learning of Irreducible Representations of Commuting Transformations

When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning

PALMER: Perception - Action Loop with Memory for Long-Horizon Planning

Training Subset Selection for Weak Supervision

Contrastive Learning as Goal-Conditioned Reinforcement Learning

CyCLIP: Cyclic Contrastive Language-Image Pretraining

Tempo: Accelerating Transformer-Based Model Training through Memory Footprint Reduction

Trading off Utility, Informativeness, and Complexity in Emergent Communication

Reduced Representation of Deformation Fields for Effective Non-rigid Shape Matching

Revisiting Neural Scaling Laws in Language and Vision

FourierFormer: Transformer Meets Generalized Fourier Integral Theorem

Real-Valued Backpropagation is Unsuitable for Complex-Valued Neural Networks

Enhanced Bilevel Optimization via Bregman Distance

Adaptive Multi-stage Density Ratio Estimation for Learning Latent Space Energy-based Model

Learning Robust Rule Representations for Abstract Reasoning via Internal Inferences

Saliency-Aware Neural Architecture Search

Training with More Confidence: Mitigating Injected and Natural Backdoors During Training

First is Better Than Last for Language Data Influence

When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment

Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation

A simple but strong baseline for online continual learning: Repeated Augmented Rehearsal

Maximum Likelihood Training of Implicit Nonlinear Diffusion Model

On Divergence Measures for Bayesian Pseudocoresets

Towards Practical Few-shot Query Sets: Transductive Minimum Description Length Inference

MABSplit: Faster Forest Training Using Multi-Armed Bandits

Reconstructing Training Data From Trained Neural Networks

Information-Theoretic Safe Exploration with Gaussian Processes

Pruning’s Effect on Generalization Through the Lens of Training and Regularization

End-to-end Algorithm Synthesis with Recurrent Networks: Extrapolation without Overthinking

Conformal Prediction with Temporal Quantile Adjustments

Expected Frequency Matrices of Elections: Computation, Geometry, and Preference Learning

Fast Bayesian Inference with Batch Bayesian Quadrature via Kernel Recombination

Online PAC-Bayes Learning

On the inability of Gaussian process regression to optimally learn compositional functions

Online Agnostic Multiclass Boosting

Beyond the Best: Distribution Functional Estimation in Infinite-Armed Bandits

Efficient Submodular Optimization under Noise: Local Search is Robust

Adversarially Robust Learning: A Generic Minimax Optimal Learner and Characterization

A Regret-Variance Trade-Off in Online Learning

On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias

Off-Policy Evaluation for Episodic Partially Observable Markov Decision Processes under Non-Parametric Models

Probabilistic Missing Value Imputation for Mixed Categorical and Ordered Data

Double Bubble, Toil and Trouble: Enhancing Certified Robustness through Transitivity

Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization

Coresets for Vertical Federated Learning: Regularized Linear Regression and $K$-Means Clustering

Active Bayesian Causal Inference

All Politics is Local: Redistricting via Local Fairness

Sequence Model Imitation Learning with Unobserved Contexts

Anticipating Performativity by Predicting from Predictions

Graphein - a Python Library for Geometric Deep Learning and Network Analysis on Biomolecular Structures and Interaction Networks

The computational and learning benefits of Daleian neural networks

Optimal Algorithms for Decentralized Stochastic Variational Inequalities

Theory and Approximate Solvers for Branched Optimal Transport with Multiple Sources

Algorithms with Prediction Portfolios

Logical Activation Functions: Logit-space equivalents of Probabilistic Boolean Operators

Understanding the Eluder Dimension

A Projection-free Algorithm for Constrained Stochastic Multi-level Composition Optimization

Robust Model Selection and Nearly-Proper Learning for GMMs

On Gap-dependent Bounds for Offline Reinforcement Learning

Perfect Sampling from Pairwise Comparisons

Fast Stochastic Composite Minimization and an Accelerated Frank-Wolfe Algorithm under Parallelization

Finding Correlated Equilibrium of Constrained Markov Game: A Primal-Dual Approach

Multi-block-Single-probe Variance Reduced Estimator for Coupled Compositional Optimization

Provably expressive temporal graph networks

What's the Harm? Sharp Bounds on the Fraction Negatively Affected by Treatment

Dynamic Fair Division with Partial Information

On Computing Probabilistic Explanations for Decision Trees

Anonymized Histograms in Intermediate Privacy Models

List-Decodable Sparse Mean Estimation via Difference-of-Pairs Filtering

The First Optimal Acceleration of High-Order Methods in Smooth Convex Optimization

Near-Optimal Sample Complexity Bounds for Constrained MDPs

Verification and search algorithms for causal DAGs

Learning and Covering Sums of Independent Random Variables with Unbounded Support

Fast Mixing of Stochastic Gradient Descent with Normalization and Weight Decay

Robust Testing in High-Dimensional Sparse Models

Dynamic Tensor Product Regression

Semi-supervised Active Linear Regression

Quantum Speedups of Optimizing Approximately Convex Functions with Applications to Logarithmic Regret Stochastic Convex Bandits

Independence Testing for Bounded Degree Bayesian Networks

Re-Analyze Gauss: Bounds for Private Matrix Approximation via Dyson Brownian Motion

Context-Based Dynamic Pricing with Partially Linear Demand Model

Extra-Newton: A First Approach to Noise-Adaptive Accelerated Second-Order Methods

Neural Lyapunov Control of Unknown Nonlinear Systems with Stability Guarantees

Causal Inference with Non-IID Data using Linear Graphical Models

Submodular Maximization in Clean Linear Time

Continuously Tempered PDMP samplers

Regret Bounds for Multilabel Classification in Sparse Label Regimes

Provable Benefit of Multitask Representation Learning in Reinforcement Learning

BEER: Fast $O(1/T)$ Rate for Decentralized Nonconvex Optimization with Communication Compression

Incrementality Bidding via Reinforcement Learning under Mixed and Delayed Rewards

DataMUX: Data Multiplexing for Neural Networks

Adaptively Exploiting d-Separators with Causal Bandits

Spending Thinking Time Wisely: Accelerating MCTS with Virtual Expansions

Toward Efficient Robust Training against Union of $\ell_p$ Threat Models

Inverse Game Theory for Stackelberg Games: the Blessing of Bounded Rationality

Global Normalization for Streaming Speech Recognition in a Modular Framework

Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline

DeepInteraction: 3D Object Detection via Modality Interaction

Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Dataset

Planning for Sample Efficient Imitation Learning

On Enforcing Better Conditioned Meta-Learning for Rapid Few-Shot Adaptation

Polynomial Neural Fields for Subband Decomposition and Manipulation

Improving Self-Supervised Learning by Characterizing Idealized Representations

Deep Ensembles Work, But Are They Necessary?

Learning to Mitigate AI Collusion on Economic Platforms

Hamiltonian Latent Operators for content and motion disentanglement in image sequences

Posterior Collapse of a Linear Latent Variable Model

TREC: Transient Redundancy Elimination-based Convolution

Unsupervised Reinforcement Learning with Contrastive Intrinsic Control

Learnable Polyphase Sampling for Shift Invariant and Equivariant Convolutional Networks

Unsupervised Cross-Task Generalization via Retrieval Augmentation

Self-Supervised Learning Through Efference Copies

Aligning individual brains with fused unbalanced Gromov Wasserstein

Formalizing Consistency and Coherence of Representation Learning

Non-deep Networks

Mining Unseen Classes via Regional Objectness: A Simple Baseline for Incremental Segmentation

Class-Dependent Label-Noise Learning with Cycle-Consistency Regularization

Solving Quantitative Reasoning Problems with Language Models

GENIE: Higher-Order Denoising Diffusion Solvers

Estimating the Arc Length of the Optimal ROC Curve and Lower Bounding the Maximal AUC

Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class

Fuzzy Learning Machine

Second Thoughts are Best: Learning to Re-Align With Human Values from Text Edits

Grounded Video Situation Recognition

Robust Neural Posterior Estimation and Statistical Model Criticism

RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning

Instance-based Learning for Knowledge Base Completion

Sub-exponential time Sum-of-Squares lower bounds for Principal Components Analysis

Tight Mutual Information Estimation With Contrastive Fenchel-Legendre Optimization

A Rotated Hyperbolic Wrapped Normal Distribution for Hierarchical Representation Learning

Finding and Listing Front-door Adjustment Sets

SALSA: Attacking Lattice Cryptography with Transformers

Automatic differentiation of nonsmooth iterative algorithms

Learning from a Sample in Online Algorithms

Trajectory of Mini-Batch Momentum: Batch Size Saturation and Convergence in High Dimensions

Improved Algorithms for Neural Active Learning

Matching in Multi-arm Bandit with Collision

A Spectral Approach to Item Response Theory

JAWS: Auditing Predictive Uncertainty Under Covariate Shift

Bessel Equivariant Networks for Inversion of Transmission Effects in Multi-Mode Optical Fibres

MetricFormer: A Unified Perspective of Correlation Exploring in Similarity Learning

ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings

Learning Recourse on Instance Environment to Enhance Prediction Accuracy

Spherization Layer: Representation Using Only Angles

Disentangling the Predictive Variance of Deep Ensembles through the Neural Tangent Kernel

Agreement-on-the-line: Predicting the Performance of Neural Networks under Distribution Shift

Efficient and Stable Fully Dynamic Facility Location

Coresets for Wasserstein Distributionally Robust Optimization Problems

Differentially Private Online-to-batch for Smooth Losses

How Transferable are Video Representations Based on Synthetic Data?

SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehicles

GLOBEM Dataset: Multi-Year Datasets for Longitudinal Human Behavior Modeling Generalization

DABS 2.0: Improved Datasets and Algorithms for Universal Self-Supervision

GOOD: A Graph Out-of-Distribution Benchmark

AnoShift: A Distribution Shift Benchmark for Unsupervised Anomaly Detection

MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge

EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine

DART: Articulated Hand Model with Diverse Accessories and Rich Textures

HandMeThat: Human-Robot Communication in Physical and Social Environments

The Dollar Street Dataset: Images Representing the Geographic and Socioeconomic Diversity of the World

PulseImpute: A Novel Benchmark Task for Pulsative Physiological Signal Imputation

Unravelling the Performance of Physics-informed Graph Neural Networks for Dynamical Systems

Enabling Detailed Action Recognition Evaluation Through Video Dataset Augmentation

Multi-LexSum: Real-world Summaries of Civil Rights Lawsuits at Multiple Granularities

SurDis: A Surface Discontinuity Dataset for Wearable Technology to Assist Blind Navigation in Urban Environments

Ontologue: Declarative Benchmark Construction for Ontological Multi-Label Classification

StrokeRehab: A Benchmark Dataset for Sub-second Action Identification

A new dataset for multilingual keyphrase generation

Communicating Natural Programs to Humans and Machines

ComMU: Dataset for Combinatorial Music Generation

The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset

This is the way: designing and compiling LEPISZCZE, a comprehensive NLP benchmark for Polish

Flare7K: A Phenomenological Nighttime Flare Removal Dataset

Online Nonnegative CP-dictionary Learning for Markovian Data

Supervised Dimensionality Reduction and Visualization using Centroid-Encoder

Accelerated Zeroth-Order and First-Order Momentum Methods from Mini to Minimax Optimization

Joint Estimation and Inference for Data Integration Problems based on Multiple Multi-layered Gaussian Graphical Models

[Re] Explaining in Style: Training a GAN to explain a classifier in StyleSpace

[Re] Replication Study of DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks

[Re] Value Alignment Verification

(ends 4:00 PM)

4 p.m.

Competition:

NeurIPS 2022 Competition Track: Overview & Results

(ends 6:00 PM)

WED 30 NOV

6 a.m.

Registration Desk

(ends 4:00 PM)

7:30 a.m.

Invited Talk:

Interaction-Centric AI

Juho Kim

(ends 8:30 AM)

8:30 a.m.

Break:

Coffee Break

(ends 9:00 AM)

9 a.m.

Poster Session 3 [9:00-11:00]

Machine Learning on Graphs: A Model and Comprehensive Taxonomy

Cost-Sensitive Self-Training for Optimizing Non-Decomposable Metrics

Discovering and Overcoming Limitations of Noise-engineered Data-free Knowledge Distillation

Exploration via Elliptical Episodic Bonuses

Uni[MASK]: Unified Inference in Sequential Decision Problems

Learning to Navigate Wikipedia by Taking Random Walks

Reinforcement Learning with Neural Radiance Fields

Few-Shot Audio-Visual Learning of Environment Acoustics

You Can’t Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environments

Decision-Focused Learning without Decision-Making: Learning Locally Optimized Decision Losses

Understanding and Improving Robustness of Vision Transformers through Patch-based Negative Augmentation

Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo

Local Latent Space Bayesian Optimization over Structured Inputs

Bayesian Clustering of Neural Spiking Activity Using a Mixture of Dynamic Poisson Factor Analyzers

Spherical Channels for Modeling Atomic Interactions

Understanding the Evolution of Linear Regions in Deep Reinforcement Learning

A General Framework for Auditing Differentially Private Machine Learning

CHIMLE: Conditional Hierarchical IMLE for Multimodal Conditional Image Synthesis

On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learning

Efficient Non-Parametric Optimizer Search for Diverse Tasks

Transform Once: Efficient Operator Learning in Frequency Domain

Sparse Interaction Additive Networks via Feature Interaction Detection and Sparse Selection

Meta-Learning Dynamics Forecasting Using Task Inference

Implicit Neural Representations with Levels-of-Experts

Towards Theoretically Inspired Neural Initialization Optimization

Improving GANs with A Dynamic Discriminator

Towards Learning Universal Hyperparameter Optimizers with Transformers

Graph Self-supervised Learning with Accurate Discrepancy Learning

A2: Efficient Automated Attacker for Boosting Adversarial Training

Boosting Out-of-distribution Detection with Typical Features

Unified Optimal Transport Framework for Universal Domain Adaptation

Geometric Order Learning for Rank Estimation

MACK: Multimodal Aligned Conceptual Knowledge for Unpaired Image-text Matching

Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection

Meta-Learning with Self-Improving Momentum Target

GBA: A Tuning-free Approach to Switch between Synchronous and Asynchronous Training for Recommendation Models

CryptoGCN: Fast and Scalable Homomorphically Encrypted Graph Convolutional Network Inference

Semi-supervised Vision Transformers at Scale

AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition

Fine-Tuning Pre-Trained Language Models Effectively by Optimizing Subnetworks Adaptively

Self-Supervised Visual Representation Learning with Semantic Grouping

Geometry-aware Two-scale PIFu Representation for Human Reconstruction

360-MLC: Multi-view Layout Consistency for Self-training and Hyper-parameter Tuning

FeLMi : Few shot Learning with hard Mixup

Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification

Descent Steps of a Relation-Aware Energy Produce Heterogeneous Graph Neural Networks

One-shot Neural Backdoor Erasing via Adversarial Weight Masking

BILCO: An Efficient Algorithm for Joint Alignment of Time Series

LOT: Layer-wise Orthogonal Training on Improving l2 Certified Robustness

Momentum Adversarial Distillation: Handling Large Distribution Shifts in Data-Free Knowledge Distillation

AutoMTL: A Programming Framework for Automating Efficient Multi-Task Learning

Learning to Discover and Detect Objects

Transfer Learning on Heterogeneous Feature Spaces for Treatment Effects Estimation

Unsupervised Learning of Group Invariant and Equivariant Representations

Towards Understanding Grokking: An Effective Theory of Representation Learning

DMAP: a Distributed Morphological Attention Policy for learning to locomote with a changing body

Decentralized Training of Foundation Models in Heterogeneous Environments

Model-based Lifelong Reinforcement Learning with Bayesian Exploration

Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation

FedSR: A Simple and Effective Domain Generalization Method for Federated Learning

Sample-Then-Optimize Batch Neural Thompson Sampling

Improving Diffusion Models for Inverse Problems using Manifold Constraints

FedAvg with Fine Tuning: Local Updates Lead to Representation Learning

Optimal Transport-based Identity Matching for Identity-invariant Facial Expression Recognition

Orthogonal Transformer: An Efficient Vision Transformer Backbone with Token Orthogonalization

Jump Self-attention: Capturing High-order Statistics in Transformers

Flamingo: a Visual Language Model for Few-Shot Learning

Visual Prompting via Image Inpainting

MAtt: A Manifold Attention Network for EEG Decoding

Distilled Gradient Aggregation: Purify Features for Input Attribution in the Deep Neural Network

Visual Concepts Tokenization

Bi-directional Weakly Supervised Knowledge Distillation for Whole Slide Image Classification

HierSpeech: Bridging the Gap between Text and Speech by Hierarchical Variational Inference using Self-supervised Representations for Speech Synthesis

Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning

Weighted Mutual Learning with Diversity-Driven Model Compression

Understanding Benign Overfitting in Gradient-Based Meta Learning

Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attack

TransTab: Learning Transferable Tabular Transformers Across Tables

Federated Learning from Pre-Trained Models: A Contrastive Learning Approach

Multi-objective Deep Data Generation with Correlated Property Control

Learning to Sample and Aggregate: Few-shot Reasoning over Temporal Knowledge Graphs

The Policy-gradient Placement and Generative Routing Neural Networks for Chip Design

Staircase Attention for Recurrent Processing of Sequences

On the Stability and Scalability of Node Perturbation Learning

Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity

Doubly Robust Counterfactual Classification

PlasticityNet: Learning to Simulate Metal, Sand, and Snow for Optimization Time Integration

Neural Estimation of Submodular Functions with Applications to Differentiable Subset Selection

Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare

Learning to Branch with Tree MDPs

Generalization Bounds for Stochastic Gradient Descent via Localized $\varepsilon$-Covers

Global Linear and Local Superlinear Convergence of IRLS for Non-Smooth Robust Regression

A Unifying Framework for Online Optimization with Long-Term Constraints

Beyond IID: data-driven decision-making in heterogeneous environments

Consistent Interpolating Ensembles via the Manifold-Hilbert Kernel

Optimal Efficiency-Envy Trade-Off via Optimal Transport

On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL

On the Epistemic Limits of Personalized Prediction

Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees

Multi-Class $H$-Consistency Bounds

Debiased Machine Learning without Sample-Splitting for Stable Estimators

The Sample Complexity of One-Hidden-Layer Neural Networks

coVariance Neural Networks

On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach

Learning from Few Samples: Transformation-Invariant SVMs with Composition and Locality at Multiple Scales

Adaptive Data Debiasing through Bounded Exploration

Enhancing Safe Exploration Using Safety State Augmentation

Leveraging the Hints: Adaptive Bidding in Repeated First-Price Auctions

Off-Policy Evaluation for Action-Dependent Non-stationary Environments

Lower Bounds and Nearly Optimal Algorithms in Distributed Learning with Communication Compression

Bounding and Approximating Intersectional Fairness through Marginal Fairness

Brownian Noise Reduction: Maximizing Privacy Subject to Accuracy Constraints

Asynchronous SGD Beats Minibatch SGD Under Arbitrary Delays

A Reduction to Binary Approach for Debiasing Multiclass Datasets

Post-hoc estimators for learning to defer to an expert

A Closer Look at Learned Optimization: Stability, Robustness, and Inductive Biases

The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift

Policy Gradient With Serial Markov Chain Reasoning

Beyond neural scaling laws: beating power law scaling via data pruning

Left Heavy Tails and the Effectiveness of the Policy and Value Networks in DNN-based best-first search for Sokoban Planning

Uncertainty-Aware Reinforcement Learning for Risk-Sensitive Player Evaluation in Sports Game

Structure-Aware Image Segmentation with Homotopy Warping

PhysGNN: A Physics--Driven Graph Neural Network Based Model for Predicting Soft Tissue Deformation in Image--Guided Neurosurgery

Generating Long Videos of Dynamic Scenes

Rethinking Individual Global Max in Cooperative Multi-Agent Reinforcement Learning

Towards Reasonable Budget Allocation in Untargeted Graph Structure Attacks via Gradient Debias

SInGE: Sparsity via Integrated Gradients Estimation of Neuron Relevance

Learning to Drop Out: An Adversarial Approach to Training Sequence VAEs

Torsional Diffusion for Molecular Conformer Generation

Personalized Online Federated Learning with Multiple Kernels

Normalizing Flows for Knockoff-free Controlled Feature Selection

Efficiency Ordering of Stochastic Gradient Descent

Learning Bipartite Graphs: Heavy Tails and Multiple Components

Batch Bayesian optimisation via density-ratio estimation with guarantees

Discovery of Single Independent Latent Variable

Self-Similarity Priors: Neural Collages as Differentiable Fractal Representations

Graph Coloring via Neural Networks for Haplotype Assembly and Viral Quasispecies Reconstruction

Better Uncertainty Calibration via Proper Scores for Classification and Beyond

Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations

Rotation-Equivariant Conditional Spherical Neural Fields for Learning a Natural Illumination Prior

Understanding Programmatic Weak Supervision via Source-aware Influence Function

CoPur: Certifiably Robust Collaborative Inference via Feature Purification

TA-GATES: An Encoding Scheme for Neural Network Architectures

MaskPlace: Fast Chip Placement via Reinforced Visual Representation Learning

BiMLP: Compact Binary Architectures for Vision Multi-Layer Perceptrons

ORIENT: Submodular Mutual Information Measures for Data Subset Selection under Distribution Shift

Learning to Reconstruct Missing Data from Spatiotemporal Graphs with Sparse Observations

Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentation

Rethinking Value Function Learning for Generalization in Reinforcement Learning

Weighted Distillation with Unlabeled Examples

A Theoretical View on Sparsely Activated Networks

Deep Learning Methods for Proximal Inference via Maximum Moment Restriction

Stability and Generalization Analysis of Gradient Methods for Shallow Neural Networks

A Quantitative Geometric Approach to Neural-Network Smoothness

Large-Scale Differentiable Causal Discovery of Factor Graphs

Off-Team Learning

Neural Basis Models for Interpretability

Semantic Exploration from Language Abstractions and Pretrained Representations

Deconfounded Representation Similarity for Comparison of Neural Networks

If Influence Functions are the Answer, Then What is the Question?

Early Stage Convergence and Global Convergence of Training Mildly Parameterized Neural Networks

Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments

Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent

Challenging Common Assumptions in Convex Reinforcement Learning

Max-Min Off-Policy Actor-Critic Method Focusing on Worst-Case Robustness to Model Misspecification

Contrastive Neural Ratio Estimation

Symmetry Teleportation for Accelerated Optimization

VectorAdam for Rotation Equivariant Geometry Optimization

Neural Stochastic PDEs: Resolution-Invariant Learning of Continuous Spatiotemporal Dynamics

Constrained Predictive Coding as a Biologically Plausible Model of the Cortical Hierarchy

Fault-Aware Neural Code Rankers

End-to-end Symbolic Regression with Transformers

Masked Prediction: A Parameter Identifiability View

Moment Distributionally Robust Tree Structured Prediction

Inference and Sampling for Archimax Copulas

Operative dimensions in unconstrained connectivity of recurrent neural networks

Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Flexible Diffusion Modeling of Long Videos

Free Probability for predicting the performance of feed-forward fully connected neural networks

Gold-standard solutions to the Schrödinger equation using deep learning: How much physics do we need?

Manifold Interpolating Optimal-Transport Flows for Trajectory Inference

Reinforcement Learning with a Terminator

DigGAN: Discriminator gradIent Gap Regularization for GAN Training with Limited Data

Multi-Agent Reinforcement Learning is a Sequence Modeling Problem

Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation

VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids

Symmetry-induced Disentanglement on Graphs

An efficient graph generative model for navigating ultra-large combinatorial synthesis libraries

STaR: Bootstrapping Reasoning With Reasoning

Learning Physics Constrained Dynamics Using Autoencoders

LAMP: Extracting Text from Gradients with Language Model Priors

Imbalance Trouble: Revisiting Neural-Collapse Geometry

ComENet: Towards Complete and Efficient Message Passing for 3D Molecular Graphs

Improved Imaging by Invex Regularizers with Global Optima Guarantees

Trade-off between Payoff and Model Rewards in Shapley-Fair Collaborative Machine Learning

Follow-the-Perturbed-Leader for Adversarial Markov Decision Processes with Bandit Feedback

Learning from Distributed Users in Contextual Linear Bandits Without Sharing the Context

Consistency of Constrained Spectral Clustering under Graph Induced Fair Planted Partitions

Adversarial Reprogramming Revisited

AutoML Two-Sample Test

A Communication-efficient Algorithm with Linear Convergence for Federated Minimax Learning

Randomized Sketches for Clustering: Fast and Optimal Kernel $k$-Means

On-Demand Sampling: Learning Optimally from Multiple Distributions

Constrained Langevin Algorithms with L-mixing External Random Variables

Gradient-Free Methods for Deterministic and Stochastic Nonsmooth Nonconvex Optimization

Fair Wrapping for Black-box Predictions

Do Residual Neural Networks discretize Neural Ordinary Differential Equations?

Recipe for a General, Powerful, Scalable Graph Transformer

Confident Adaptive Language Modeling

Are AlphaZero-like Agents Robust to Adversarial Perturbations?

Non-rigid Point Cloud Registration with Neural Deformation Pyramid

Peripheral Vision Transformer

Mind Reader: Reconstructing complex images from brain activities

RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer

Few-shot Relational Reasoning via Connection Subgraph Pretraining

ASPiRe: Adaptive Skill Priors for Reinforcement Learning

Point Transformer V2: Grouped Vector Attention and Partition-based Pooling

M³ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design

Deep Compression of Pre-trained Transformer Models

A Variational Edge Partition Model for Supervised Graph Representation Learning

MCMAE: Masked Convolution Meets Masked Autoencoders

Neural-Symbolic Entangled Framework for Complex Query Answering

SwinTrack: A Simple and Strong Baseline for Transformer Tracking

OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models

Learning Neural Acoustic Fields

Subgroup Robustness Grows On Trees: An Empirical Baseline Investigation

Interpolation and Regularization for Causal Learning

Blackbox Attacks via Surrogate Ensemble Search

Green Hierarchical Vision Transformer for Masked Image Modeling

A Practical, Progressively-Expressive GNN

Improving Neural Ordinary Differential Equations with Nesterov's Accelerated Gradient Method

Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime

Between Stochastic and Adversarial Online Convex Optimization: Improved Regret Bounds via Smoothness

DeepTOP: Deep Threshold-Optimal Policy for MDPs and RMABs

Learning Symmetric Rules with SATNet

Evaluation beyond Task Performance: Analyzing Concepts in AlphaZero in Hex

Distributionally Adaptive Meta Reinforcement Learning

HyperTree Proof Search for Neural Theorem Proving

You Only Live Once: Single-Life Reinforcement Learning

CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion

Are all Frames Equal? Active Sparse Labeling for Video Action Detection

The Impact of Task Underspecification in Evaluating Deep Reinforcement Learning

Diffusion-LM Improves Controllable Text Generation

Variable-rate hierarchical CPC leads to acoustic unit discovery in speech

Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equations

Stochastic Adaptive Activation Function

Benefits of Permutation-Equivariance in Auction Mechanisms

Random Sharpness-Aware Minimization

On-Device Training Under 256KB Memory

Factorized-FL: Personalized Federated Learning with Parameter Factorization & Similarity Matching

A Closer Look at Prototype Classifier for Few-shot Image Classification

On the Strong Correlation Between Model Invariance and Generalization

“Why Not Other Classes?”: Towards Class-Contrastive Back-Propagation Explanations

Parameter-Efficient Masking Networks

Make Some Noise: Reliable and Efficient Single-Step Adversarial Training

ZooD: Exploiting Model Zoo for Out-of-Distribution Generalization

One Positive Label is Sufficient: Single-Positive Multi-Label Learning with Label Enhancement

Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters

Identifiability of deep generative models without auxiliary information

Beyond spectral gap: the role of the topology in decentralized learning

Change-point Detection for Sparse and Dense Functional Data in General Dimensions

Invariant and Transportable Representations for Anti-Causal Domain Shifts

Robust Feature-Level Adversaries are Interpretability Tools

Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks

Anonymous Bandits for Multi-User Systems

Branch & Learn for Recursively and Iteratively Solvable Problems in Predict+Optimize

Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity

Reproducibility in Optimization: Theoretical Framework and Limits

Adversarial Robustness is at Odds with Lazy Training

The Curse of Unrolling: Rate of Differentiating Through Optimization

On the Theoretical Properties of Noise Correlation in Stochastic Optimization

Support Recovery in Sparse PCA with Incomplete Data

Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits

A gradient estimator via L1-randomization for online zero-order optimization with two point feedback

Hypothesis Testing for Differentially Private Linear Regression

Sound and Complete Causal Identification with Latent Variables Given Local Background Knowledge

One for All: Simultaneous Metric and Preference Learning over Multiple Users

AdaFocal: Calibration-aware Adaptive Focal Loss

Learning Distributed and Fair Policies for Network Load Balancing as Markov Potential Game

Fair Ranking with Noisy Protected Attributes

Off-Policy Evaluation with Deficient Support Using Side Information

How to talk so AI will learn: Instructions, descriptions, and autonomy

Capturing Failures of Large Language Models via Human Cognitive Biases

A time-resolved theory of information encoding in recurrent neural networks

Learning Chaotic Dynamics in Dissipative Systems

On Elimination Strategies for Bandit Fixed-Confidence Identification

(Optimal) Online Bipartite Matching with Degree Information

Scalable and Efficient Non-adaptive Deterministic Group Testing

Subspace clustering in high-dimensions: Phase transitions & Statistical-to-Computational gap

A Few Expert Queries Suffices for Sample-Efficient RL with Resets and Linear Value Approximation

Sample Complexity of Learning Heuristic Functions for Greedy-Best-First and A* Search

Distributionally Robust Optimization via Ball Oracle Acceleration

Online Bipartite Matching with Advice: Tight Robustness-Consistency Tradeoffs for the Two-Stage Model

GraB: Finding Provably Better Data Permutations than Random Reshuffling

House of Cans: Covert Transmission of Internal Datasets via Capacity-Aware Neuron Steganography

A Causal Analysis of Harm

Simple Mechanisms for Welfare Maximization in Rich Advertising Auctions

On Image Segmentation With Noisy Labels: Characterization and Volume Properties of the Optimal Solutions to Accuracy and Dice

Online Algorithms for the Santa Claus Problem

Learning on the Edge: Online Learning with Stochastic Feedback Graphs

Optimal Dynamic Regret in LQR Control

Improved Regret Analysis for Variance-Adaptive Linear Bandits and Horizon-Free Linear Mixture MDPs

Optimistic Mirror Descent Either Converges to Nash or to Strong Coarse Correlated Equilibria in Bimatrix Games

Online Convex Optimization with Hard Constraints: Towards the Best of Two Worlds and Beyond

Pessimism for Offline Linear Contextual Bandits using $\ell_p$ Confidence Sets

Mean Estimation in High-Dimensional Binary Markov Gaussian Mixture Models

Queue Up Your Regrets: Achieving the Dynamic Capacity Region of Multiplayer Bandits

The First Optimal Algorithm for Smooth and Strongly-Convex-Strongly-Concave Minimax Optimization

Beyond black box densities: Parameter learning for the deviated components

A Best-of-Both-Worlds Algorithm for Bandits with Delayed Feedback

New Lower Bounds for Private Estimation and a Generalized Fingerprinting Lemma

Policy Optimization for Markov Games: Unified Framework and Faster Convergence

A Damped Newton Method Achieves Global $\mathcal O \left(\frac{1}{k^2}\right)$ and Local Quadratic Convergence Rate

Local Identifiability of Deep ReLU Neural Networks: the Theory

Conditional Independence Testing with Heteroskedastic Data and Applications to Causal Discovery

Online Allocation and Learning in the Presence of Strategic Agents

Signal Recovery with Non-Expansive Generative Network Priors

Practical Adversarial Multivalid Conformal Prediction

Sublinear Algorithms for Hierarchical Clustering

Large-scale Optimization of Partial AUC in a Range of False Positive Rates

Stability Analysis and Generalization Bounds of Adversarial Training

Globally Gated Deep Linear Networks

Generalization Analysis on Learning with a Concurrent Verifier

Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagation

Test Time Adaptation via Conjugate Pseudo-labels

Best of Both Worlds Model Selection

Logical Credal Networks

Low-Rank Modular Reinforcement Learning via Muscle Synergy

LogiGAN: Learning Logical Reasoning via Adversarial Pre-training

Self-supervised surround-view depth estimation with volumetric feature fusion

Promising or Elusive? Unsupervised Object Segmentation from Real-world Single Images

Learning to Attack Federated Learning: A Model-based Reinforcement Learning Attack Framework

Sparse Probabilistic Circuits via Pruning and Growing

Explaining Preferences with Shapley Values

Implications of Model Indeterminacy for Explanations of Automated Decisions

Self-Explaining Deviations for Coordination

A Direct Approximation of AIXI Using Logical State Abstractions

Adjoint-aided inference of Gaussian process driven differential equations

Beyond L1: Faster and Better Sparse Models with skglm

Robust Imitation of a Few Demonstrations with a Backwards Model

Improving Policy Learning via Language Dynamics Distillation

Monocular Dynamic View Synthesis: A Reality Check

VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programming

Test-Time Training with Masked Autoencoders

Learning Modular Simulations for Homogeneous Systems

Flowification: Everything is a normalizing flow

Focal Modulation Networks

OpenAUC: Towards AUC-Oriented Open-Set Recognition

Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations

Contrastive Adapters for Foundation Model Group Robustness

Two-layer neural network on infinite dimensional data: global optimization guarantee in the mean-field regime

Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspective

Riemannian Neural SDE: Learning Stochastic Representations on Manifolds

Discovering Design Concepts for CAD Sketches

🏘️ ProcTHOR: Large-Scale Embodied AI Using Procedural Generation

Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?

Risk-Driven Design of Perception Systems

Finding Differences Between Transformers and ConvNets Using Counterfactual Simulation Testing

On the Generalization Power of the Overfitted Three-Layer Neural Tangent Kernel Model

Escaping from the Barren Plateau via Gaussian Initializations in Deep Variational Quantum Circuits

On Deep Generative Models for Approximation and Estimation of Distributions on Manifolds

Constants of motion network

Graph Scattering beyond Wavelet Shackles

On Margins and Generalisation for Voting Classifiers

Stochastic Online Learning with Feedback Graphs: Finite-Time and Asymptotic Optimality

Learning Infinite-Horizon Average-Reward Restless Multi-Action Bandits via Index Awareness

Conservative Dual Policy Optimization for Efficient Model-Based Reinforcement Learning

Provable Defense against Backdoor Policies in Reinforcement Learning

Cost-efficient Gaussian tensor network embeddings for tensor-structured inputs

Online Learning and Pricing for Network Revenue Management with Reusable Resources

MultiScan: Scalable RGBD scanning for 3D environments with articulated objects

FairVFL: A Fair Vertical Federated Learning Framework with Contrastive Adversarial Learning

DeepFoids: Adaptive Bio-Inspired Fish Simulation with Deep Reinforcement Learning

Bayesian Spline Learning for Equation Discovery of Nonlinear Dynamics with Quantified Uncertainty

Understanding Non-linearity in Graph Neural Networks from the Bayesian-Inference Perspective

Graph Reordering for Cache-Efficient Near Neighbor Search

Boosting Barely Robust Learners: A New Perspective on Adversarial Robustness

The Gyro-Structure of Some Matrix Manifolds

Revisit last-iterate convergence of mSGD under milder requirement on step size

Robustness Analysis of Video-Language Models Against Visual and Language Perturbations

Beyond Real-world Benchmark Datasets: An Empirical Study of Node Classification with GNNs

AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentation

JAHS-Bench-201: A Foundation For Research On Joint Architecture And Hyperparameter Search

Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time

Towards Better Evaluation for Dynamic Link Prediction

Avalon: A Benchmark for RL Generalization Using Procedurally Generated Worlds

GriddlyJS: A Web IDE for Reinforcement Learning

AnimeRun: 2D Animation Visual Correspondence from Open Source 3D Movies

VLMbench: A Compositional Benchmark for Vision-and-Language Manipulation

OpenFilter: A Framework to Democratize Research Access to Social Media AR Filters

Forecasting Future World Events With Neural Networks

Active-Passive SimStereo - Benchmarking the Cross-Generalization Capabilities of Deep Learning-based Stereo Methods

TAP-Vid: A Benchmark for Tracking Any Point in a Video

EHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health Records

IKEA-Manual: Seeing Shape Assembly Step by Step

Model Zoos: A Dataset of Diverse Populations of Neural Network Models

mRI: Multi-modal 3D Human Pose Estimation Dataset using mmWave, RGB-D, and Inertial Sensors

A Multi-Task Benchmark for Korean Legal Language Understanding and Judgement Prediction

Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models

A Large Scale Search Dataset for Unbiased Learning to Rank

Open High-Resolution Satellite Imagery: The WorldStrat Dataset – With Application to Super-Resolution

Sample Efficiency Matters: A Benchmark for Practical Molecular Optimization

MSDS: A Large-Scale Chinese Signature and Token Digit String Dataset for Handwriting Verification

Truncated Emphatic Temporal Difference Methods for Prediction and Control

IALE: Imitating Active Learner Ensembles

Fast and Robust Rank Aggregation against Model Misspecification

All You Need is a Good Functional Prior for Bayesian Deep Learning

[Re] Solving Phase Retrieval With a Learned Reference

[Re] Strategic classification made practical: reproduction

[Re] Graph Edit Networks

(ends 11:00 AM)

12:30 p.m.

Invited Talk:

Blueprint for an AI Bill of Rights Making Automated Systems Work for the American People

Alondra Nelson

(ends 1:30 PM)

1:30 p.m.

Break:

Coffee Break

(ends 2:00 PM)

2 p.m.

Poster Session 4 [2:00-4:00]

Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data

Active Learning Through a Covering Lens

Sparse Winning Tickets are Data-Efficient Image Recognizers

Active Learning Helps Pretrained Models Learn the Intended Task

Star Temporal Classification: Sequence Modeling with Partially Labeled Data

S-PIFu: Integrating Parametric Human Models with PIFu for Single-view Clothed Human Reconstruction

Interaction-Grounded Learning with Action-Inclusive Feedback

Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm

NCP: Neural Correspondence Prior for Effective Unsupervised Shape Matching

Environment Diversification with Multi-head Neural Network for Invariant Learning

Denoising Diffusion Restoration Models

Predictive Coding beyond Gaussian Distributions

Trajectory balance: Improved credit assignment in GFlowNets

The least-control principle for local learning at equilibrium

Universally Expressive Communication in Multi-Agent Reinforcement Learning

Introspective Learning : A Two-Stage approach for Inference in Neural Networks

Exploit Reward Shifting in Value-Based Deep-RL: Optimistic Curiosity-Based Exploration and Conservative Exploitation via Linear Reward Shaping

Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis

ToDD: Topological Compound Fingerprinting in Computer-Aided Drug Discovery

Spartan: Differentiable Sparsity via Regularized Transportation

S3GC: Scalable Self-Supervised Graph Clustering

HUMUS-Net: Hybrid Unrolled Multi-scale Network Architecture for Accelerated MRI Reconstruction

DreamShard: Generalizable Embedding Table Placement for Recommender Systems

Navigating Memory Construction by Global Pseudo-Task Simulation for Continual Learning

Graph Learning Assisted Multi-Objective Integer Programming

CEIP: Combining Explicit and Implicit Priors for Reinforcement Learning with Demonstrations

Roadblocks for Temporarily Disabling Shortcuts and Learning New Knowledge

Contrastive Graph Structure Learning via Information Bottleneck for Recommendation

Mining Multi-Label Samples from Single Positive Labels

Reinforced Genetic Algorithm for Structure-based Drug Design

Adaptive Distribution Calibration for Few-Shot Learning with Hierarchical Optimal Transport

CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP

Class-Aware Adversarial Transformers for Medical Image Segmentation

Debiased Self-Training for Semi-Supervised Learning

Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning

Single-Stage Visual Relationship Learning using Conditional Queries

Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging

DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection

OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point Clouds

Physically-Based Face Rendering for NIR-VIS Face Recognition

HSurf-Net: Normal Estimation for 3D Point Clouds by Learning Hyper Surfaces

Scaling Multimodal Pre-Training via Cross-Modality Gradient Harmonization

Deep Bidirectional Language-Knowledge Graph Pretraining

Vision Transformers provably learn spatial structure

Rethinking and Improving Robustness of Convolutional Neural Networks: a Shapley Value-based Approach in Frequency Domain

Self-Supervised Fair Representation Learning without Demographics

Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing

Sequence-to-Set Generative Models

Does GNN Pretraining Help Molecular Representation?

Visual correspondence-based explanations improve AI robustness and human-AI team accuracy

Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens

Probabilistic Transformer: Modelling Ambiguities and Distributions for RNA Folding and Molecule Design

Transformers from an Optimization Perspective

Human-Robotic Prosthesis as Collaborating Agents for Symmetrical Walking

Locating and Editing Factual Associations in GPT

Embed and Emulate: Learning to estimate parameters of dynamical systems with uncertainty quantification

Guaranteed Conservation of Momentum for Learning Particle-based Fluid Dynamics

DOMINO: Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning

UniGAN: Reducing Mode Collapse in GANs using a Uniform Generator

On the Convergence Theory for Hessian-Free Bilevel Algorithms

Meta-Auto-Decoder for Solving Parametric Partial Differential Equations

Deep Active Learning by Leveraging Training Dynamics

Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence

Invertible Monotone Operators for Normalizing Flows

S$^3$-NeRF: Neural Reflectance Field from Shading and Shadow under a Single Viewpoint

Cross-Linked Unified Embedding for cross-modality representation learning

u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modality

A Closer Look at the Adversarial Robustness of Deep Equilibrium Models

A Transformer-Based Object Detector with Coarse-Fine Crossing Representations

Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networks

Semi-Supervised Semantic Segmentation via Gentle Teaching Assistant

BinauralGrad: A Two-Stage Conditional Diffusion Probabilistic Model for Binaural Audio Synthesis

Deep Attentive Belief Propagation: Integrating Reasoning and Learning for Solving Constraint Optimization Problems

Robust Calibration with Multi-domain Temperature Scaling

CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks

Data-Efficient Augmentation for Training Neural Networks

Learning Distinct and Representative Modes for Image Captioning

GraphDE: A Generative Framework for Debiased Learning and Out-of-Distribution Detection on Graphs

Bootstrapped Transformer for Offline Reinforcement Learning

INRAS: Implicit Neural Representation for Audio Scenes

AMP: Automatically Finding Model Parallel Strategies with Heterogeneity Awareness

On the Symmetries of Deep Learning Models and their Internal Representations

Gradient Descent: The Ultimate Optimizer

Maximizing Revenue under Market Shrinkage and Market Uncertainty

Constraining Gaussian Processes to Systems of Linear Ordinary Differential Equations

Neural Set Function Extensions: Learning with Discrete Functions in High Dimensions

In Defense of the Unitary Scalarization for Deep Multi-Task Learning

A Unified Analysis of Federated Learning with Arbitrary Client Participation

DNA: Proximal Policy Optimization with a Dual Network Architecture

Sampling in Constrained Domains with Orthogonal-Space Variational Gradient Descent

Sampling without Replacement Leads to Faster Rates in Finite-Sum Minimax Optimization

Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPs

Gradient Descent Is Optimal Under Lower Restricted Secant Inequality And Upper Error Bound

Posterior and Computational Uncertainty in Gaussian Processes

Luckiness in Multiscale Online Learning

Learning-Augmented Algorithms for Online Linear and Semidefinite Programming

Dynamic Pricing with Monotonicity Constraint under Unknown Parametric Demand Model

An Asymptotically Optimal Batched Algorithm for the Dueling Bandit Problem

Precise Regret Bounds for Log-loss via a Truncated Bayesian Algorithm

The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization

Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks

Training Scale-Invariant Neural Networks on the Sphere Can Happen in Three Regimes

A Data-Augmentation Is Worth A Thousand Samples: Analytical Moments And Sampling-Free Training

Causal Discovery in Heterogeneous Environments Under the Sparse Mechanism Shift Hypothesis

Maximizing and Satisficing in Multi-armed Bandits with Graph Information

Thompson Sampling Efficiently Learns to Control Diffusion Processes

Counterfactual Fairness with Partially Known Causal Graph

Non-Convex Bilevel Games with Critical Point Selection Maps

Provably tuning the ElasticNet across instances

On Learning and Refutation in Noninteractive Local Differential Privacy

Learning in Observable POMDPs, without Computationally Intractable Oracles

On the Robustness of Graph Neural Diffusion to Topology Perturbations

Robust Learning against Relational Adversaries

Toward Understanding Privileged Features Distillation in Learning-to-Rank

Lifting Weak Supervision To Structured Prediction

Meta Reinforcement Learning with Finite Training Tasks - a Density Estimation Approach

Symbolic Distillation for Learned TCP Congestion Control

On the Effectiveness of Persistent Homology

Fairness without Demographics through Knowledge Distillation

Pre-Trained Model Reusability Evaluation for Small-Data Transfer Learning

HSDF: Hybrid Sign and Distance Field for Modeling Surfaces with Arbitrary Topologies

Where to Pay Attention in Sparse Training for Feature Selection?

An Adaptive Kernel Approach to Federated Learning of Heterogeneous Causal Effects

RényiCL: Contrastive Representation Learning with Skew Rényi Divergence

Look where you look! Saliency-guided Q-networks for generalization in visual Reinforcement Learning

On Embeddings for Numerical Features in Tabular Deep Learning

SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery

(De-)Randomized Smoothing for Decision Stump Ensembles

Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning

Wasserstein $K$-means for clustering probability distributions

Coordinate Linear Variance Reduction for Generalized Linear Programming

Proximal Point Imitation Learning

Pitfalls of Epistemic Uncertainty Quantification through Loss Minimisation

Why neural networks find simple solutions: The many regularizers of geometric complexity

Learning Articulated Rigid Body Dynamics with Lagrangian Graph Neural Network

Learning interacting dynamical systems with latent Gaussian process ODEs

Capturing Graphs with Hypo-Elliptic Diffusions

MOVE: Unsupervised Movable Object Segmentation and Detection

3DILG: Irregular Latent Grids for 3D Generative Modeling

Unsupervised Multi-Object Segmentation by Predicting Probable Motion Patterns

Learning Concept Credible Models for Mitigating Shortcuts

Efficient Scheduling of Data Augmentation for Deep Reinforcement Learning

BayesPCN: A Continually Learnable Predictive Coding Associative Memory

DeVRF: Fast Deformable Voxel Radiance Fields for Dynamic Scenes

ATD: Augmenting CP Tensor Decomposition by Self Supervision

Robust Models are less Over-Confident

HF-NeuS: Improved Surface Reconstruction Using High-Frequency Details

ELIAS: End-to-End Learning to Index and Search in Large Output Spaces

Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold

DISCO: Adversarial Defense with Local Implicit Functions

Invariance-Aware Randomized Smoothing Certificates

Bayesian inference via sparse Hamiltonian flows

Score-based Generative Modeling Secretly Minimizes the Wasserstein Distance

Relational Reasoning via Set Transformers: Provable Efficiency and Applications to MARL

Robustness to Unbounded Smoothness of Generalized SignSGD

Doubly-Asynchronous Value Iteration: Making Value Iteration Asynchronous in Actions

Associating Objects and Their Effects in Video through Coordination Games

Masked Autoencoding for Scalable and Generalizable Decision Making

In the Eye of the Beholder: Robust Prediction with Causal User Modeling

Autoregressive Perturbations for Data Poisoning

Generalization Analysis of Message Passing Neural Networks on Large Random Graphs

Local Metric Learning for Off-Policy Evaluation in Contextual Bandits with Continuous Actions

Graph Neural Network Bandits

Learning Two-Player Markov Games: Neural Function Approximation and Correlated Equilibrium

Bayesian Optimization over Discrete and Mixed Spaces via Probabilistic Reparameterization

Grounding Aleatoric Uncertainty for Unsupervised Environment Design

BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach

A Theoretical Framework for Inference Learning

High-dimensional Additive Gaussian Processes under Monotonicity Constraints

On the generalization of learning algorithms that do not converge

Proppo: a Message Passing Framework for Customizable and Composable Learning Algorithms

FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation

Reinforcement Learning with Non-Exponential Discounting

A Multi-Resolution Framework for U-Nets with Applications to Hierarchical VAEs

A Lagrangian Duality Approach to Active Learning

Non-identifiability and the Blessings of Misspecification in Models of Molecular Fitness

Uncalibrated Models Can Improve Human-AI Collaboration

Increasing Confidence in Adversarial Robustness Evaluations

Procedural Image Programs for Representation Learning

Structuring Representations Using Group Invariants

Most Activation Functions Can Win the Lottery Without Excessive Depth

Structural Kernel Search via Bayesian Optimization and Symbolical Optimal Transport

Faster Deep Reinforcement Learning with Slower Online Network

Online Reinforcement Learning for Mixed Policy Scopes

What are the best Systems? New Perspectives on NLP Benchmarking

ALMA: Hierarchical Learning for Composite Multi-Agent Tasks

Intra-agent speech permits zero-shot task acquisition

Deep Multi-Modal Structural Equations For Causal Effect Estimation With Unstructured Proxies

Hybrid Neural Autoencoders for Stimulus Encoding in Visual and Other Sensory Neuroprostheses

Data Distributional Properties Drive Emergent In-Context Learning in Transformers

Drawing out of Distribution with Neuro-Symbolic Generative Models

FIRE: Semantic Field of Words Represented as Non-Linear Functions

Do Current Multi-Task Optimization Methods in Deep Learning Even Help?

Diffusion Models as Plug-and-Play Priors

ESCADA: Efficient Safety and Context Aware Dose Allocation for Precision Medicine

Robust Bayesian Regression via Hard Thresholding

Optimal-er Auctions through Attention

Multi-Fidelity Best-Arm Identification

Adaptive Oracle-Efficient Online Learning

Towards Consistency in Adversarial Classification

Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks

Beyond Adult and COMPAS: Fair Multi-Class Prediction via Information Projection

Multi-block Min-max Bilevel Optimization with Applications in Multi-task Deep AUC Maximization

A Single-timescale Analysis for Stochastic Approximation with Multiple Coupled Sequences

A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits

Evaluated CMI Bounds for Meta Learning: Tightness and Expressiveness

Discrete-Convex-Analysis-Based Framework for Warm-Starting Algorithms with Predictions

projUNN: efficient method for training deep networks with unitary matrices

$\alpha$-ReQ : Assessing Representation Quality in Self-Supervised Learning by measuring eigenspectrum decay

Structural Knowledge Distillation for Object Detection

Scalable Interpretability via Polynomials

An empirical analysis of compute-optimal large language model training

Object Scene Representation Transformer

Generative Neural Articulated Radiance Fields

Hand-Object Interaction Image Generation

Paraphrasing Is All You Need for Novel Object Captioning

A Theoretical Study on Solving Continual Learning

RecursiveMix: Mixed Learning with History

Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs

GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models

Multiview Human Body Reconstruction from Uncalibrated Cameras

Multivariate Time-Series Forecasting with Temporal Polynomial Graph Neural Networks

RainNet: A Large-Scale Imagery Dataset and Benchmark for Spatial Precipitation Downscaling

Alleviating "Posterior Collapse'' in Deep Topic Models via Policy Gradient

Refining Low-Resource Unsupervised Translation by Language Disentanglement of Multilingual Translation Model

ZeroC: A Neuro-Symbolic Model for Zero-shot Concept Recognition and Acquisition at Inference Time

Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules

What Can the Neural Tangent Kernel Tell Us About Adversarial Robustness?

Understanding Hyperdimensional Computing for Parallel Single-Pass Learning

Injecting Domain Knowledge from Empirical Interatomic Potentials to Neural Networks for Predicting Material Properties

Accelerating Sparse Convolution with Column Vector-Wise Sparsity

Exact Shape Correspondence via 2D graph convolution

Global Optimal K-Medoids Clustering of One Million Samples

Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise

Sample-Efficient Reinforcement Learning of Partially Observable Markov Games

FasterRisk: Fast and Accurate Interpretable Risk Scores

LieGG: Studying Learned Lie Group Generators

Shield Decentralization for Safe Multi-Agent Reinforcement Learning

ProtoX: Explaining a Reinforcement Learning Agent via Prototyping

On the Generalizability and Predictability of Recommender Systems

Adversarial Unlearning: Reducing Confidence Along Adversarial Directions

Neurosymbolic Deep Generative Models for Sequence Data with Relational Constraints

Memory Efficient Continual Learning with Transformers

Inverse Design for Fluid-Structure Interactions using Graph Network Simulators

Cross-modal Learning for Image-Guided Point Cloud Shape Completion

Beyond Mahalanobis Distance for Textual OOD Detection

Panchromatic and Multispectral Image Fusion via Alternating Reverse Filtering Network

Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study

Tight Analysis of Extra-gradient and Optimistic Gradient Methods For Nonconvex Minimax Problems

Look More but Care Less in Video Recognition

Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation

APG: Adaptive Parameter Generation Network for Click-Through Rate Prediction

Rethinking the Reverse-engineering of Trojan Triggers

The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning

Exploring evolution-aware & -free protein language models as protein function predictors

M$^4$I: Multi-modal Models Membership Inference

Deep Model Reassembly

Incorporating Bias-aware Margins into Contrastive Loss for Collaborative Filtering

Stochastic Multiple Target Sampling Gradient Descent

Probable Domain Generalization via Quantile Risk Minimization

Fair and Optimal Decision Trees: A Dynamic Programming Approach

An Information-Theoretic Framework for Deep Learning

Learning Tractable Probabilistic Models from Inconsistent Local Estimates

Domain Adaptation meets Individual Fairness. And they get along.

Recurrent Convolutional Neural Networks Learn Succinct Learning Algorithms

Interventions, Where and How? Experimental Design for Causal Models at Scale

On A Mallows-type Model For (Ranked) Choices

Forward-Backward Latent State Inference for Hidden Continuous-Time semi-Markov Chains

Regret Bounds for Risk-Sensitive Reinforcement Learning

Rate-Optimal Online Convex Optimization in Adaptive Linear Control

Zonotope Domains for Lagrangian Neural Network Verification

Generalizing Bayesian Optimization with Decision-theoretic Entropies

Regularized Gradient Descent Ascent for Two-Player Zero-Sum Markov Games

Wasserstein Logistic Regression with Mixed Features

The Role of Baselines in Policy Gradient Optimization

Active Learning Polynomial Threshold Functions

Quantile Constrained Reinforcement Learning: A Reinforcement Learning Framework Constraining Outage Probability

Generalised Implicit Neural Representations

Score-Based Generative Models Detect Manifolds

Mixture-of-Experts with Expert Choice Routing

Coresets for Relational Data and The Applications

Factored Adaptation for Non-Stationary Reinforcement Learning

Counterfactual harm

Addressing Leakage in Concept Bottleneck Models

Compositional generalization through abstract representations in human and artificial neural networks

Efficient coding, channel capacity, and the emergence of retinal mosaics

Learning in Congestion Games with Bandit Feedback

Optimal Weak to Strong Learning

Log-Linear-Time Gaussian Processes Using Binary Tree Kernels

Sharp Analysis of Stochastic Optimization under Global Kurdyka-Lojasiewicz Inequality

Learning Distributions Generated by Single-Layer ReLU Networks in the Presence of Arbitrary Outliers

Instance-optimal PAC Algorithms for Contextual Bandits

Learning the Structure of Large Networked Systems Obeying Conservation Laws

Local Linear Convergence of Gradient Methods for Subspace Optimization via Strict Complementarity

A Near-Optimal Primal-Dual Method for Off-Policy Learning in CMDP

The alignment property of SGD noise and how it helps select flat minima: A stability analysis

Weisfeiler and Leman Go Walking: Random Walk Kernels Revisited

Polynomial-Time Optimal Equilibria with a Mediator in Extensive-Form Games

An $\alpha$-regret analysis of Adversarial Bilateral Trade

Algorithms and Hardness for Learning Linear Thresholds from Label Proportions

Decomposable Non-Smooth Convex Optimization with Nearly-Linear Gradient Oracle Complexity

Optimal Query Complexities for Dynamic Trace Estimation

On Scalable Testing of Samplers

Private Isotonic Regression

Neural Network Architecture Beyond Width and Depth

Faster and Scalable Algorithms for Densest Subgraph and Decomposition

Differentially Private Covariance Revisited

A Fourier Approach to Mixture Learning

On Non-Linear operators for Geometric Deep Learning

Linear Label Ranking with Bounded Noise

Estimation of Entropy in Constant Space with Improved Sample Complexity

Efficient Sampling on Riemannian Manifolds via Langevin MCMC

Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedback

Understanding Deep Neural Function Approximation in Reinforcement Learning via $\epsilon$-Greedy Exploration

Communication-efficient distributed eigenspace estimation with arbitrary node failures

Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent

Causal Discovery in Linear Latent Variable Models Subject to Measurement Error

Log-Concave and Multivariate Canonical Noise Distributions for Differential Privacy

A Quadrature Rule combining Control Variates and Adaptive Importance Sampling

Decision Trees with Short Explainable Rules

Task-level Differentially Private Meta Learning

Zeroth-Order Hard-Thresholding: Gradient Error vs. Expansivity

Robust Imitation via Mirror Descent Inverse Reinforcement Learning

Learning Partial Equivariances From Data

Exploitability Minimization in Games and Beyond

Communication-Efficient Topologies for Decentralized Learning with $O(1)$ Consensus Rate

Hardness in Markov Decision Processes: Theory and Practice

Finding Optimal Arms in Non-stochastic Combinatorial Bandits with Semi-bandit Feedback and Finite Budget

Decoupled Context Processing for Context Augmented Language Modeling

PerfectDou: Dominating DouDizhu with Perfect Information Distillation

Neural Transmitted Radiance Fields

Self-Supervised Pretraining for Large-Scale Point Clouds

GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesis

Streaming Radiance Fields for 3D Video Synthesis

MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields

Analyzing Data-Centric Properties for Graph Contrastive Learning

On the Limitations of Stochastic Pre-processing Defenses

Hedging as Reward Augmentation in Probabilistic Graphical Models

Riemannian Score-Based Generative Modelling

On the Spectral Bias of Convolutional Neural Tangent and Gaussian Process Kernels

Causality Preserving Chaotic Transformation and Classification using Neurochaos Learning

Exploring through Random Curiosity with General Value Functions

Masked Autoencoders that Listen

Sharing Knowledge for Meta-learning with Feature Descriptions

ReFactor GNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective

New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound

Non-Markovian Reward Modelling from Trajectory Labels via Interpretable Multiple Instance Learning

FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

Conditional Diffusion Process for Inverse Halftoning

Prompt Certified Machine Unlearning with Randomized Gradient Smoothing and Quantization

Training language models to follow instructions with human feedback

Learning to Accelerate Partial Differential Equations via Latent Global Evolution

Robust $\phi$-Divergence MDPs

Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression

Translation-equivariant Representation in Recurrent Networks with a Continuous Manifold of Attractors

Visual Clues: Bridging Vision and Language Foundations for Image Paragraph Captioning

Learning Audio-Visual Dynamics Using Scene Graphs for Audio Source Separation

Towards a Standardised Performance Evaluation Protocol for Cooperative MARL

Mismatched No More: Joint Model-Policy Optimization for Model-Based RL

Continual Learning with Evolving Class Ontologies

The Franz-Parisi Criterion and Computational Trade-offs in High Dimensional Statistics

Conformalized Fairness via Quantile Regression

Neural Differential Equations for Learning to Program Neural Nets Through Continuous Learning Rules

An Analysis of Ensemble Sampling

Resolving the data ambiguity for periodic crystals

Split-kl and PAC-Bayes-split-kl Inequalities for Ternary Random Variables

On the Sample Complexity of Stabilizing LTI Systems on a Single Trajectory

On the convergence of policy gradient methods to Nash equilibria in general stochastic games

Certifying Some Distributional Fairness with Subpopulation Decomposition

Biologically Inspired Dynamic Thresholds for Spiking Neural Networks

Precise Learning Curves and Higher-Order Scalings for Dot-product Kernel Regression

Towards a Unified Framework for Uncertainty-aware Nonlinear Variable Selection with Theoretical Guarantees

Sketching based Representations for Robust Image Classification with Provable Guarantees

Causality-driven Hierarchical Structure Discovery for Reinforcement Learning

Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners

Foundation Posteriors for Approximate Probabilistic Inference

Unsupervised Image-to-Image Translation with Density Changing Regularization

Pruning Neural Networks via Coresets and Convex Geometry: Towards No Assumptions

Overparameterization from Computational Constraints

Learn to Match with No Regret: Reinforcement Learning in Markov Matching Markets

Unknown-Aware Domain Adversarial Learning for Open-Set Domain Adaptation

Giga-scale Kernel Matrix-Vector Multiplication on GPU

USB: A Unified Semi-supervised Learning Benchmark for Classification

DC-BENCH: Dataset Condensation Benchmark

FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings

NAS-Bench-Suite-Zero: Accelerating Research on Zero Cost Proxies

PROSPECT: Labeled Tandem Mass Spectrometry Dataset for Machine Learning in Proteomics

FLAIR: Federated Learning Annotated Image Repository

The Surprising Effectiveness of PPO in Cooperative Multi-Agent Games

ConfLab: A Data Collection Concept, Dataset, and Benchmark for Machine Analysis of Free-Standing Social Interactions in the Wild

MOMA-LRG: Language-Refined Graphs for Multi-Object Multi-Actor Activity Parsing

Touch and Go: Learning from Human-Collected Vision and Touch

A Survey and Datasheet Repository of Publicly Available US Criminal Justice Datasets

MATE: Benchmarking Multi-Agent Reinforcement Learning in Distributed Target Coverage Control

How Would The Viewer Feel? Estimating Wellbeing From Video Scenarios

MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control

OpenSRH: optimizing brain tumor surgery using intraoperative stimulated Raman histology

DDXPlus: A New Dataset For Automatic Medical Diagnosis

ViSioNS: Visual Search in Natural Scenes Benchmark

NeoRL: A Near Real-World Benchmark for Offline Reinforcement Learning

Finding Naturally Occurring Physical Backdoors in Image Datasets

AirfRANS: High Fidelity Computational Fluid Dynamics Dataset for Approximating Reynolds-Averaged Navier–Stokes Solutions

OpenXAI: Towards a Transparent Evaluation of Model Explanations

LAION-5B: An open large-scale dataset for training next generation image-text models

OccGen: Selection of Real-world Multilingual Parallel Data Balanced in Gender within Occupations

Fairness-Aware PAC Learning from Corrupted Data

LSAR: Efficient Leverage Score Sampling Algorithm for the Analysis of Big Time Series Data

Multi-Agent Multi-Armed Bandits with Limited Communication

When is the Convergence Time of Langevin Algorithms Dimension Independent? A Composite Optimization Viewpoint

[Re] Nondeterminism and Instability in Neural Network Optimization

[Re] Replication Study of "Fairness and Bias in Online Selection"

[Re] Reproduction and Extension of "Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation"

[Re] Learning to count everything

(ends 4:00 PM)

4 p.m.

Town Hall:

NeurIPS Town Hall

(ends 5:00 PM)

THU 1 DEC

6 a.m.

Registration Desk

(ends 4:00 PM)

7:30 a.m.

Invited Talk:

The Data-Centric Era: How ML is Becoming an Experimental Science

Isabelle Guyon

(ends 8:30 AM)

8:30 a.m.

Break:

Coffee Break

(ends 9:00 AM)

9 a.m.

Poster Session 5 [9:00-11:00]

Learning Operators with Coupled Attention

Single Model Uncertainty Estimation via Stochastic Data Centering

A Neural Pre-Conditioning Active Learning Algorithm to Reduce Label Complexity

Retaining Knowledge for Learning with Dynamic Definition

Amortized Inference for Causal Structure Learning

Multi-Game Decision Transformers

NS3: Neuro-symbolic Semantic Code Search

NeMF: Neural Motion Fields for Kinematic Animation

COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics

Towards Safe Reinforcement Learning with a Safety Editor Policy

A Solver-free Framework for Scalable Learning in Neural ILP Architectures

Chroma-VAE: Mitigating Shortcut Learning with Generative Classifiers

Bivariate Causal Discovery for Categorical Data via Classification with Optimal Label Permutation

Concrete Score Matching: Generalized Score Matching for Discrete Data

Structuring Uncertainty for Fine-Grained Sampling in Stochastic Segmentation Networks

NOMAD: Nonlinear Manifold Decoders for Operator Learning

Modeling Human Exploration Through Resource-Rational Reinforcement Learning

Hierarchical classification at multiple operating points

Instance-Based Uncertainty Estimation for Gradient-Boosted Regression Trees

Sparsity in Continuous-Depth Neural Networks

Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning

Diagonal State Spaces are as Effective as Structured State Spaces

UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes

Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos

Cluster and Aggregate: Face Recognition with Large Probe Set

Reinforcement Learning with Automated Auxiliary Loss Search

Distribution-Informed Neural Networks for Domain Adaptation Regression

Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?

Association Graph Learning for Multi-Task Classification with Category Shifts

Adv-Attribute: Inconspicuous and Transferable Adversarial Attack on Face Recognition

OST: Improving Generalization of DeepFake Detection via One-Shot Test-Time Training

Grow and Merge: A Unified Framework for Continuous Categories Discovery

Revisiting Sliced Wasserstein on Images: From Vectorization to Convolution

Meta-Complementing the Semantics of Short Texts in Neural Topic Models

Learning Equivariant Segmentation with Instance-Unique Querying

DivBO: Diversity-aware CASH for Ensemble Learning

Towards Efficient Post-training Quantization of Pre-trained Language Models

FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction

How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders

Transferring Pre-trained Multimodal Representations with Cross-modal Similarity Matching

A Neural Corpus Indexer for Document Retrieval

I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification

ElasticMVS: Learning elastic part representation for self-supervised multi-view stereopsis

Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Experts

DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations

MaskTune: Mitigating Spurious Correlations by Forcing to Explore

Neuron with Steady Response Leads to Better Generalization

Invariance Learning based on Label Hierarchy

Bidirectional Learning for Offline Infinite-width Model-based Optimization

Energy-Based Contrastive Learning of Visual Representations

FR: Folded Rationalization with a Unified Encoder

Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models

Unsupervised Adaptation from Repeated Traversals for Autonomous Driving

Generating multivariate time series with COmmon Source CoordInated GAN (COSCI-GAN)

Unsupervised Learning of Equivariant Structure from Sequences

An Analytical Theory of Curriculum Learning in Teacher-Student Networks

Lifelong Neural Predictive Coding: Learning Cumulatively Online without Forgetting

MAgNet: Mesh Agnostic Neural PDE Solver

Iterative Structural Inference of Directed Graphs

Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning

A Unifying Framework of Off-Policy General Value Function Evaluation

Langevin Autoencoders for Learning Deep Latent Variable Models

SketchBoost: Fast Gradient Boosted Decision Tree for Multioutput Problems

Your Transformer May Not be as Powerful as You Expect

GRASP: Navigating Retrosynthetic Planning with Goal-driven Policy

High-Order Pooling for Graph Neural Networks with Tensor Decomposition

TreeMoCo: Contrastive Neuron Morphology Representation Learning

SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos

TVLT: Textless Vision-Language Transformer

Molecule Generation by Principal Subgraph Mining and Assembling

AttCAT: Explaining Transformers via Attentive Class Activation Tokens

Joint Learning of 2D-3D Weakly Supervised Semantic Segmentation

Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling

Expansion and Shrinkage of Localization for Weakly-Supervised Semantic Segmentation

Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discrimination

Generalized Delayed Feedback Model with Post-Click Information in Recommender Systems

Phase Transition from Clean Training to Adversarial Training

On the Robustness of Deep Clustering Models: Adversarial Attacks and Defenses

LIFT: Language-Interfaced Fine-Tuning for Non-language Machine Learning Tasks

Improving 3D-aware Image Synthesis with A Geometry-aware Discriminator

Watermarking for Out-of-distribution Detection

Neural Temporal Walks: Motif-Aware Representation Learning on Continuous-Time Dynamic Graphs

InsNet: An Efficient, Flexible, and Performant Insertion-based Text Generation Model

Prune and distill: similar reformatting of image information along rat visual cortex and deep neural networks

Is this the Right Neighborhood? Accurate and Query Efficient Model Agnostic Explanations

Recruitment Strategies That Take a Chance

Experimental Design for Linear Functionals in Reproducing Kernel Hilbert Spaces

Physics-Informed Implicit Representations of Equilibrium Network Flows

Modeling Transitivity and Cyclicity in Directed Graphs via Binary Code Box Embeddings

Collaborative Learning of Discrete Distributions under Heterogeneity and Communication Constraints

A Boosting Approach to Reinforcement Learning

Active Learning with Neural Networks: Insights from Nonparametric Statistics

Optimal Scaling for Locally Balanced Proposals in Discrete Spaces

Non-Stationary Bandits under Recharging Payoffs: Improved Planning with Sublinear Regret

Effective Dimension in Bandit Problems under Censorship

Partial Identification of Treatment Effects with Implicit Generative Models

A Universal Error Measure for Input Predictions Applied to Online Graph Problems

Minimax Regret for Cascading Bandits

Defining and Characterizing Reward Gaming

Beyond Time-Average Convergence: Near-Optimal Uncoupled Online Learning via Clairvoyant Multiplicative Weights Update

Non-convex online learning via algorithmic equivalence

Annihilation of Spurious Minima in Two-Layer ReLU Networks

On global convergence of ResNets: From finite to infinite width using linear parameterization

GULP: a prediction-based metric between representations

A Combinatorial Perspective on the Optimization of Shallow ReLU Networks

Learning sparse features can lead to overfitting in neural networks

Conformal Off-Policy Prediction in Contextual Bandits

Movement Penalized Bayesian Optimization with Application to Wind Energy Systems

Identifiability and generalizability from multiple experts in Inverse Reinforcement Learning

The Implicit Delta Method

Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers

Archimedes Meets Privacy: On Privately Estimating Quantiles in High Dimensions Under Minimal Assumptions

Markovian Interference in Experiments

Whitening Convergence Rate of Coupling-based Normalizing Flows

When Does Differentially Private Learning Not Suffer in High Dimensions?

DASCO: Dual-Generator Adversarial Support Constrained Offline Reinforcement Learning

Are GANs overkill for NLP?

Positive-Unlabeled Learning using Random Forests via Recursive Greedy Risk Minimization

Direct Advantage Estimation

Simplified Graph Convolution with Heterophily

GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Games

Exploration-Guided Reward Shaping for Reinforcement Learning under Sparse Rewards

Relational Proxies: Emergent Relationships as Fine-Grained Discriminators

Time-Conditioned Dances with Simplicial Complexes: Zigzag Filtration Curve based Supra-Hodge Convolution Networks for Time-series Forecasting

MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators

Learning Individualized Treatment Rules with Many Treatments: A Supervised Clustering Approach Using Adaptive Fusion

Exploiting the Relationship Between Kendall's Rank Correlation and Cosine Similarity for Attribution Protection

Back Razor: Memory-Efficient Transfer Learning by Self-Sparsified Backpropagation

Not All Bits have Equal Value: Heterogeneous Precisions via Trainable Noise

Pure Transformers are Powerful Graph Learners

Syndicated Bandits: A Framework for Auto Tuning Hyper-parameters in Contextual Bandit Algorithms

Bayesian Active Learning with Fully Bayesian Gaussian Processes

$k$-Sliced Mutual Information: A Quantitative Study of Scalability with Dimension

Accelerated Projected Gradient Algorithms for Sparsity Constrained Optimization Problems

Sparse Gaussian Process Hyperparameters: Optimize or Integrate?

Detecting Abrupt Changes in Sequential Pairwise Comparison Data

Seeing the forest and the tree: Building representations of both individual and collective dynamics with transformers

Learning Fractional White Noises in Neural Stochastic Differential Equations

On the Frequency-bias of Coordinate-MLPs

Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors

GAUDI: A Neural Architect for Immersive 3D Scene Generation

Learning Debiased Classifier with Biased Committee

PAC: Assisted Value Factorization with Counterfactual Predictions in Multi-Agent Reinforcement Learning

Recurrent Memory Transformer

Fast Vision Transformers with HiLo Attention

Dynamic Sparse Network for Time Series Classification: Learning What to “See”

Hyperparameter Sensitivity in Deep Outlier Detection: Analysis and a Scalable Hyper-Ensemble Solution

Extrapolative Continuous-time Bayesian Neural Network for Fast Training-free Test-time Adaptation

Unsupervised Learning for Combinatorial Optimization with Principled Objective Relaxation

Bridging the Gap: Unifying the Training and Evaluation of Neural Network Binary Classifiers

Can Hybrid Geometric Scattering Networks Help Solve the Maximum Clique Problem?

Unsupervised Learning From Incomplete Measurements for Inverse Problems

On the Double Descent of Random Features Models Trained with SGD

Generalization Properties of NAS under Activation and Skip Connection Search

Neur2SP: Neural Two-Stage Stochastic Programming

Receding Horizon Inverse Reinforcement Learning

Neural Attentive Circuits

Interaction Modeling with Multiplex Attention

Measures of Information Reflect Memorization Patterns

Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks

Sobolev Acceleration and Statistical Optimality for Learning Elliptic Equations via Gradient Descent

Blessing of Depth in Linear Regression: Deeper Models Have Flatter Landscape Around the True Solution

Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions

Proximal Learning With Opponent-Learning Awareness

ResQ: A Residual Q Function-based Approach for Multi-Agent Reinforcement Learning Value Factorization

Joint Entropy Search For Maximally-Informed Bayesian Optimization

Can Push-forward Generative Models Fit Multimodal Distributions?

Learning Interface Conditions in Domain Decomposition Solvers

Chaotic Dynamics are Intrinsic to Neural Network Training with SGD

An In-depth Study of Stochastic Backpropagation

Automatic Differentiation of Programs with Discrete Randomness

Weakly Supervised Representation Learning with Sparse Perturbations

Domain Generalization without Excess Empirical Risk

Scalable Sensitivity and Uncertainty Analyses for Causal-Effect Estimates of Continuous-Valued Interventions

Distinguishing discrete and continuous behavioral variability using warped autoregressive HMMs

Handcrafted Backdoors in Deep Neural Networks

Multitasking Models are Robust to Structural Failure: A Neural Model for Bilingual Cognitive Reserve

Representing Spatial Trajectories as Distributions

Exact Solutions of a Deep Linear Network

Systematic improvement of neural network quantum states using Lanczos

Score-Based Diffusion meets Annealed Importance Sampling

Factored DRO: Factored Distributionally Robust Policies for Contextual Bandits

On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting

Learning General World Models in a Handful of Reward-Free Deployments

LISA: Learning Interpretable Skill Abstractions from Language

SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collections

Geometric Knowledge Distillation: Topology Compression for Graph Neural Networks

FourierNets enable the design of highly non-local optical encoders for computational imaging

Learning to Scaffold: Optimizing Model Explanations for Teaching

SCONE: Surface Coverage Optimization in Unknown Environments by Volumetric Integration

VisCo Grids: Surface Reconstruction with Viscosity and Coarea Grids

A Conditional Randomization Test for Sparse Logistic Regression in High-Dimension

Reduction Algorithms for Persistence Diagrams of Networks: CoralTDA and PrunIT

A Consolidated Cross-Validation Algorithm for Support Vector Machines via Data Reduction

RISE: Robust Individualized Decision Learning with Sensitive Variables

Learning NP-Hard Multi-Agent Assignment Planning using GNN: Inference on a Random Graph and Provable Auction-Fitted Q-learning

Tractable Optimality in Episodic Latent MABs

Causal Identification under Markov equivalence: Calculus, Algorithm, and Completeness

Non-Gaussian Tensor Programs

Nonparametric Uncertainty Quantification for Single Deterministic Neural Network

Nest Your Adaptive Algorithm for Parameter-Agnostic Nonconvex Minimax Optimization

DP-PCA: Statistically Optimal and Differentially Private PCA

DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning

Acceleration in Distributed Sparse Regression

Communication Acceleration of Local Gradient Methods via an Accelerated Primal-Dual Algorithm with an Inexact Prox

Chefs' Random Tables: Non-Trigonometric Random Features

Rapid Model Architecture Adaption for Meta-Learning

UnfoldML: Cost-Aware and Uncertainty-Based Dynamic 2D Prediction for Multi-Stage Classification

Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers

MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction

Implicit Warping for Animation with Image Sets

Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space

VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts

Few-shot Image Generation via Adaptation-Aware Kernel Modulation

Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models

TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers

SPD domain-specific batch normalization to crack interpretable unsupervised domain adaptation in EEG

Locally Hierarchical Auto-Regressive Modeling for Image Generation

Deep Generative Model for Periodic Graphs

Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training

AutoST: Towards the Universal Modeling of Spatio-temporal Sequences

Egocentric Video-Language Pretraining

Learning Active Camera for Multi-Object Navigation

Maximum a posteriori natural scene reconstruction from retinal ganglion cells with deep denoiser priors

Assaying Out-Of-Distribution Generalization in Transfer Learning

Not too little, not too much: a theoretical analysis of graph (over)smoothing

The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models

Squeezeformer: An Efficient Transformer for Automatic Speech Recognition

GREED: A Neural Framework for Learning Graph Distance Functions

Zeroth-Order Negative Curvature Finding: Escaping Saddle Points without Gradients

Does Momentum Change the Implicit Regularization on Separable Data?

Lower Bounds on Randomly Preconditioned Lasso via Robust Sparse Designs

Robust On-Policy Sampling for Data-Efficient Policy Evaluation in Reinforcement Learning

Redundant representations help generalization in wide neural networks

Explainability Via Causal Self-Talk

Learn what matters: cross-domain imitation learning with task-relevant embeddings

Learning to Compare Nodes in Branch and Bound with Graph Neural Networks

MoCoDA: Model-based Counterfactual Data Augmentation

Subsidiary Prototype Alignment for Universal Domain Adaptation

A Fast Post-Training Pruning Framework for Transformers

Dynamic Inverse Reinforcement Learning for Characterizing Animal Behavior

NeuPhysics: Editable Neural Geometry and Physics from Monocular Videos

Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights

DeepMed: Semiparametric Causal Mediation Analysis with Debiased Deep Learning

Power and limitations of single-qubit native quantum neural networks

SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learning

Heatmap Distribution Matching for Human Pose Estimation

Tensor Program Optimization with Probabilistic Programs

Skills Regularized Task Decomposition for Multi-task Offline Reinforcement Learning

Benign Overfitting in Two-layer Convolutional Neural Networks

Task Discovery: Finding the Tasks that Neural Networks Generalize on

Retrieve, Reason, and Refine: Generating Accurate and Faithful Patient Instructions

NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis

MORA: Improving Ensemble Robustness Evaluation with Model Reweighing Attack

Unsupervised Representation Learning from Pre-trained Diffusion Probabilistic Models

MissDAG: Causal Discovery in the Presence of Missing Data with Continuous Additive Noise Models

Domain Adaptation under Open Set Label Shift

Lethal Dose Conjecture on Data Poisoning

Emergent Communication: Generalization and Overfitting in Lewis Games

Asymptotic Properties for Bayesian Neural Network in Besov Space

On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification

Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models

Multi-fidelity Monte Carlo: a pseudo-marginal approach

Near-Optimal Correlation Clustering with Privacy

Rethinking Variational Inference for Probabilistic Programs with Stochastic Support

Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams

Positively Weighted Kernel Quadrature via Subsampling

On the non-universality of deep learning: quantifying the cost of symmetry

Globally Convergent Policy Search for Output Estimation

Optimistic Tree Searches for Combinatorial Black-Box Optimization

Tikhonov Regularization is Optimal Transport Robust under Martingale Constraints

IMED-RL: Regret optimal learning of ergodic Markov decision processes

Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits

KSD Aggregated Goodness-of-fit Test

Latent Hierarchical Causal Structure Discovery with Rank Constraints

In Differential Privacy, There is Truth: on Vote-Histogram Leakage in Ensemble Private Learning

Explicit Tradeoffs between Adversarial and Natural Distributional Robustness

A Mean-Field Game Approach to Cloud Resource Management with Function Approximation

On Privacy and Personalization in Cross-Silo Federated Learning

Byzantine Spectral Ranking

Learning to Follow Instructions in Text-Based Games

Convergent Representations of Computer Programs in Human and Artificial Neural Networks

Emergence of Hierarchical Layers in a Single Sheet of Self-Organizing Spiking Neurons

Matrix Multiplicative Weights Updates in Quantum Zero-Sum Games: Conservation Laws & Recurrence

Structural Analysis of Branch-and-Cut and the Learnability of Gomory Mixed Integer Cuts

Exploring the Whole Rashomon Set of Sparse Decision Trees

Robust Rent Division

A Classification of $G$-invariant Shallow Neural Networks

Polynomial time guarantees for the Burer-Monteiro method

A sharp NMF result with applications in network modeling

Uncoupled Learning Dynamics with $O(\log T)$ Swap Regret in Multiplayer Games

Average Sensitivity of Euclidean k-Clustering

A gradient sampling method with complexity guarantees for Lipschitz functions in high and low dimensions

Dynamic pricing and assortment under a contextual MNL demand

Accelerating SGD for Highly Ill-Conditioned Huge-Scale Online Matrix Completion

Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)

Performative Power

Is Sortition Both Representative and Fair?

Improved Bounds on Neural Complexity for Representing Piecewise Linear Functions

Nearly-Tight Bounds for Testing Histogram Distributions

Quantum Algorithms for Sampling Log-Concave Distributions and Estimating Normalizing Constants

A consistently adaptive trust-region method

Single-pass Streaming Lower Bounds for Multi-armed Bandits Exploration with Instance-sensitive Sample Complexity

On Infinite Separations Between Simple and Optimal Mechanisms

Near-Optimal Private and Scalable $k$-Clustering

Asymptotics of smoothed Wasserstein distances in the small noise regime

Finite-Sample Maximum Likelihood Estimation of Location

High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation

Fast Distance Oracles for Any Symmetric Norm

Momentum Aggregation for Private Non-convex ERM

Differentially Private Generalized Linear Models Revisited

Thinking Outside the Ball: Optimal Learning with Gradient Descent for Generalized Linear Stochastic Convex Optimization

A Simple and Optimal Policy Design for Online Learning with Safety against Heavy-tailed Risk

Optimal and Adaptive Monteiro-Svaiter Acceleration

Continuous Deep Q-Learning in Optimal Control Problems: Normalized Advantage Functions Analysis

Falsification before Extrapolation in Causal Effect Estimation

Non-monotonic Resource Utilization in the Bandits with Knapsacks Problem

Bezier Gaussian Processes for Tall and Wide Data

A Characterization of Semi-Supervised Adversarially Robust PAC Learnability

Fairness in Federated Learning via Core-Stability

A Communication-Efficient Distributed Gradient Clipping Algorithm for Training Deep Neural Networks

Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Power

Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit

On the consistent estimation of optimal Receiver Operating Characteristic (ROC) curve

Iron: Private Inference on Transformers

Unsupervised Learning under Latent Label Shift

Decentralized, Communication- and Coordination-free Learning in Structured Matching Markets

Tsetlin Machine for Solving Contextual Bandit Problems

Learning-based Motion Planning in Dynamic Environments Using GNNs and Temporal Encoding

Mutual Information Divergence: A Unified Metric for Multimodal Generative Models

Sparse2Dense: Learning to Densify 3D Features for 3D Object Detection

AD-DROP: Attribution-Driven Dropout for Robust Language Model Fine-Tuning

Trading off Image Quality for Robustness is not Necessary with Regularized Deterministic Autoencoders

Training stochastic stabilized supralinear networks by dynamics-neutral growth

Using Mixup as a Regularizer Can Surprisingly Improve Accuracy & Out-of-Distribution Robustness

Rashomon Capacity: A Metric for Predictive Multiplicity in Classification

Parametrically Retargetable Decision-Makers Tend To Seek Power

Structured Recognition for Generative Models with Explaining Away

A Continuous Time Framework for Discrete Denoising Models

TPU-KNN: K Nearest Neighbor Search at Peak FLOP/s

Pragmatically Learning from Pedagogical Demonstrations in Multi-Goal Environments

Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding

An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learning

Emergent Graphical Conventions in a Visual Communication Game

A Geometric Perspective on Variational Autoencoders

Semantic Probabilistic Layers for Neuro-Symbolic Learning

DevFly: Bio-Inspired Development of Binary Connections for Locality Preserving Sparse Codes

Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork

NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation

Periodic Graph Transformers for Crystal Material Property Prediction

MCVD - Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation

Approximation with CNNs in Sobolev Space: with Applications to Classification

MultiGuard: Provably Robust Multi-label Classification against Adversarial Examples

Theoretically Provable Spiking Neural Networks

CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers

ReCo: Retrieve and Co-segment for Zero-shot Transfer

Online Decision Mediation

Collaborative Decision Making Using Action Suggestions

When does dough become a bagel? Analyzing the remaining mistakes on ImageNet

Toward Equation of Motion for Deep Neural Networks: Continuous-time Gradient Descent and Discretization Error Analysis

Revisiting Optimal Convergence Rate for Smooth and Non-convex Stochastic Decentralized Optimization

Differentially Private Linear Sketches: Efficient Implementations and Applications

Pruning has a disparate impact on model accuracy

Differentiable Analog Quantum Computing for Optimization and Control

CCCP is Frank-Wolfe in disguise

Towards Optimal Communication Complexity in Distributed Non-Convex Optimization

Better SGD using Second-order Momentum

Data-Efficient Structured Pruning via Submodular Optimization

Safe Opponent-Exploitation Subgame Refinement

Provably Feedback-Efficient Reinforcement Learning via Active Reward Learning

Efficient Aggregated Kernel Tests using Incomplete $U$-statistics

Feature Learning in $L_2$-regularized DNNs: Attraction/Repulsion and Sparsity

Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning

Structure-Preserving 3D Garment Modeling with Neural Sewing Machines

WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents

Few-shot Learning for Feature Selection with Hilbert-Schmidt Independence Criterion

Training and Inference on Any-Order Autoregressive Models the Right Way

BagFlip: A Certified Defense Against Data Poisoning

Dynamic Learning in Large Matching Markets

How Powerful are K-hop Message Passing Graph Neural Networks

Global Convergence of Direct Policy Search for State-Feedback $\mathcal{H}_\infty$ Robust Control: A Revisit of Nonsmooth Synthesis with Goldstein Subdifferential

CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World Domains

PEER: A Comprehensive and Multi-Task Benchmark for Protein Sequence Understanding

OpenFWI: Large-scale Multi-structural Benchmark Datasets for Full Waveform Inversion

PDEBench: An Extensive Benchmark for Scientific Machine Learning

AutoWS-Bench-101: Benchmarking Automated Weak Supervision with 100 Labels

Why do tree-based models still outperform deep learning on typical tabular data?

A Benchmark for Compositional Visual Reasoning

SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning

PeRFception: Perception using Radiance Fields

Nocturne: a scalable driving benchmark for bringing multi-agent learning one step closer to the real world

VeriDark: A Large-Scale Benchmark for Authorship Verification on the Dark Web

FACT: Learning Governing Abstractions Behind Integer Sequences

Geoclidean: Few-Shot Generalization in Euclidean Geometry

MBW: Multi-view Bootstrapping in the Wild

HAPI: A Large-scale Longitudinal Dataset of Commercial ML API Predictions

Change Event Dataset for Discovery from Spatio-temporal Remote Sensing Imagery

3DOS: Towards 3D Open Set Learning - Benchmarking and Understanding Semantic Novelty Detection on Point Clouds

K-Radar: 4D Radar Object Detection for Autonomous Driving in Various Weather Conditions

TempEL: Linking Dynamically Evolving and Newly Emerging Entities

Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability

Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark

LIPS - Learning Industrial Physical Simulation benchmark suite

Attraction-Repulsion Spectrum in Neighbor Embeddings

Decimated Framelet System on Graphs and Fast G-Framelet Transforms

On the Approximation of Cooperative Heterogeneous Multi-Agent Reinforcement Learning (MARL) using Mean Field Control (MFC)

A Unified Statistical Learning Model for Rankings and Scores with Application to Grant Panel Review

Rethinking Nonlinear Instrumental Variable Models through Prediction Validity

Sufficient reductions in regression with mixed predictors

[Re] An Implementation of Fair Robust Learning

[Re] Exacerbating Algorithmic Bias through Fairness Attacks

[Re] Transparent Object Tracking Benchmark

(ends 11:00 AM)

12:30 p.m.

Invited Talk:

The Forward-Forward Algorithm for Training Deep Neural Networks

Geoffrey Hinton

(ends 1:30 PM)

1:30 p.m.

Break:

Coffee Break

(ends 2:00 PM)

2 p.m.

Poster Session 6 [2:00-4:00]

ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models

Ambiguous Images With Human Judgments for Robust Visual Event Classification

Recovery and Generalization in Over-Realized Dictionary Learning

Self-Supervised Learning with an Information Maximization Criterion

PAC Prediction Sets for Meta-Learning

BiT: Robustly Binarized Multi-distilled Transformer

CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior

VICRegL: Self-Supervised Learning of Local Visual Features

GenSDF: Two-Stage Learning of Generalizable Signed Distance Functions

Disentangling Transfer in Continual Reinforcement Learning

Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees

TUSK: Task-Agnostic Unsupervised Keypoints

Generalization Gap in Amortized Inference

Online Deep Equilibrium Learning for Regularization by Denoising

Deep invariant networks with differentiable augmentation layers

VICE: Variational Interpretable Concept Embeddings

A contrastive rule for meta-learning

Diagnosing failures of fairness transfer across distribution shift in real-world medical settings

A Contrastive Framework for Neural Text Generation

Redeeming intrinsic rewards via constrained optimization

NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification

Model Preserving Compression for Neural Networks

Controlled Sparsity via Constrained Optimization or: How I Learned to Stop Tuning Penalties and Love Constraints

Robust Binary Models by Pruning Randomly-initialized Networks

Training Spiking Neural Networks with Local Tandem Learning

Constrained GPI for Zero-Shot Transfer in Reinforcement Learning

Improving Task-Specific Generalization in Few-Shot Learning via Adaptive Vicinal Risk Minimization

DIMES: A Differentiable Meta Solver for Combinatorial Optimization Problems

HYPRO: A Hybridly Normalized Probabilistic Model for Long-Horizon Prediction of Event Sequences

Noise Attention Learning: Enhancing Noise Robustness by Gradient Scaling

Self-Aware Personalized Federated Learning

Learning to Re-weight Examples with Optimal Transport for Imbalanced Classification

Towards Understanding the Mixture-of-Experts Layer in Deep Learning

Improved Feature Distillation via Projector Ensemble

Two-Stream Network for Sign Language Recognition and Translation

Knowledge Distillation from A Stronger Teacher

Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation

Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models

Feature-Proxy Transformer for Few-Shot Segmentation

Mask Matching Transformer for Few-Shot Segmentation

Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection

DaDA: Distortion-aware Domain Adaptation for Unsupervised Semantic Segmentation

AniFaceGAN: Animatable 3D-Aware Face Image Generation for Video Avatars

Selective compression learning of latent representations for variable-rate image compression

Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning

CascadeXML: Rethinking Transformers for End-to-end Multi-resolution Training in Extreme Multi-label Classification

Few-Shot Non-Parametric Learning with Deep Latent Variable Model

Revisiting Heterophily For Graph Neural Networks

Distributionally robust weighted k-nearest neighbors

ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers

SeqPATE: Differentially Private Text Generation via Knowledge Distillation

Inductive Logical Query Answering in Knowledge Graphs

Remember the Past: Distilling Datasets into Addressable Memories for Neural Networks

K-LITE: Learning Transferable Visual Models with External Knowledge

Diffusion Visual Counterfactual Explanations

Graph Neural Networks are Dynamic Programmers

Assistive Teaching of Motor Control Tasks to Humans

Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off

Black-box coreset variational inference

Supervising the Multi-Fidelity Race of Hyperparameter Configurations

Distributional Reward Estimation for Effective Multi-agent Deep Reinforcement Learning

Amortized Projection Optimization for Sliced Wasserstein Generative Models

CoNSoLe: Convex Neural Symbolic Learning

Sketch-GNN: Scalable Graph Neural Networks with Sublinear Training Complexity

WaveBound: Dynamic Error Bounds for Stable Time Series Forecasting

Hierarchical Channel-spatial Encoding for Communication-efficient Collaborative Learning

Spatial Pruned Sparse Convolution for Efficient 3D Object Detection

LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discovery

Self-Supervised Learning of Brain Dynamics from Broad Neuroimaging Data

Motion Transformer with Global Intention Localization and Local Movement Refinement

Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection

SemMAE: Semantic-Guided Masking for Learning Masked Autoencoders

Improving Multi-Task Generalization via Regularizing Spurious Correlation

Label-Aware Global Consistency for Multi-Label Learning with Single Positive Labels

One Model to Edit Them All: Free-Form Text-Driven Image Manipulation with Semantic Modulations

Latency-aware Spatial-wise Dynamic Networks

Why Do Artificially Generated Data Help Adversarial Robustness

Pre-activation Distributions Expose Backdoor Neurons

Recovering Private Text in Federated Learning of Language Models

Zero-shot Transfer Learning within a Heterogeneous Graph via Knowledge Transfer Networks

Towards Robust Blind Face Restoration with Codebook Lookup Transformer

S2P: State-conditioned Image Synthesis for Data Augmentation in Offline Reinforcement Learning

NeurOLight: A Physics-Agnostic Neural Operator Enabling Parametric Photonic Device Simulation

UDC: Unified DNAS for Compressible TinyML Models for Neural Processing Units

Using Embeddings for Causal Estimation of Peer Influence in Social Networks

Batch size-invariance for policy optimization

Top Two Algorithms Revisited

Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs

Biologically-Plausible Determinant Maximization Neural Networks for Blind Separation of Correlated Sources

When does return-conditioned supervised learning work for offline reinforcement learning?

Communication Efficient Distributed Learning for Kernelized Contextual Bandits

TaSIL: Taylor Series Imitation Learning

DAGMA: Learning DAGs via M-matrices and a Log-Determinant Acyclicity Characterization

Efficient Active Learning with Abstention

No-regret learning in games with noisy feedback: Faster rates and adaptivity via learning rate separation

Integral Probability Metrics PAC-Bayes Bounds

A Fast Scale-Invariant Algorithm for Non-negative Least Squares with Non-negative Data

Online Minimax Multiobjective Optimization: Multicalibeating and Other Applications

Nonstationary Dual Averaging and Online Fair Allocation

The price of unfairness in linear bandits with biased feedback

Augmenting Online Algorithms with $\varepsilon$-Accurate Predictions

A Non-Asymptotic Moreau Envelope Theory for High-Dimensional Generalized Linear Models

Spectral Bias Outside the Training Set for Deep Networks in the Kernel Regime

Symplectic Spectrum Gaussian Processes: Learning Hamiltonians from Noisy and Sparse Data

Tree Mover's Distance: Bridging Graph Metrics and Stability of Graph Neural Networks

On the Parameterization and Initialization of Diagonal State Space Models

On the Discrimination Risk of Mean Aggregation Feature Imputation in Graphs

Staggered Rollout Designs Enable Causal Inference Under Interference Without Network Knowledge

Near-Optimal Multi-Agent Learning for Safe Coverage Control

Deep Counterfactual Estimation with Categorical Background Variables

Using Partial Monotonicity in Submodular Maximization

A New Family of Generalization Bounds Using Samplewise Evaluated CMI

Tight Lower Bounds on Worst-Case Guarantees for Zero-Shot Learning with Attributes

Bellman Residual Orthogonalization for Offline Reinforcement Learning

Riemannian Diffusion Models

Formulating Robustness Against Unforeseen Attacks

Characterizing Datapoints via Second-Split Forgetting

Fairness Transferability Subject to Bounded Distribution Shift

Oracle Inequalities for Model Selection in Offline Reinforcement Learning

Simulation-guided Beam Search for Neural Combinatorial Optimization

Stars: Tera-Scale Graph Building for Clustering and Learning

Estimating and Explaining Model Performance When Both Covariates and Labels Shift

Simultaneous Missing Value Imputation and Structure Learning with Groups

Signal Processing for Implicit Neural Representations

Regularized Molecular Conformation Fields

GAL: Gradient Assisted Learning for Decentralized Multi-Organization Collaborations

When Does Group Invariant Learning Survive Spurious Correlations?

Diverse Weight Averaging for Out-of-Distribution Generalization

KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation

Data Augmentation for Compositional Data: Advancing Predictive Models of the Microbiome

Improving Certified Robustness via Statistical Learning with Logical Reasoning

Cooperative Distribution Alignment via JSD Upper Bound

Generalization Bounds with Minimal Dependency on Hypothesis Class via Distributionally Robust Optimization

Minimax Optimal Fixed-Budget Best Arm Identification in Linear Bandits

Markov Chain Score Ascent: A Unifying Framework of Variational Inference with Markovian Gradients

A Kernelised Stein Statistic for Assessing Implicit Generative Models

Effects of Data Geometry in Early Deep Learning

Deep Differentiable Logic Gate Networks

Exploring the Latent Space of Autoencoders with Interventional Assays

Semi-Discrete Normalizing Flows through Differentiable Tessellation

Video Diffusion Models

What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputs

Generative multitask learning mitigates target-causing confounding

Adversarial Task Up-sampling for Meta-learning

DHRL: A Graph-Based Approach for Long-Horizon and Sparse Hierarchical Reinforcement Learning

Entropy-Driven Mixed-Precision Quantization for Deep Network Design

Efficient and Effective Augmentation Strategy for Adversarial Training

Dataset Inference for Self-Supervised Models

Exposing and Exploiting Fine-Grained Block Structures for Fast and Accurate Sparse Training

Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?

Alleviating Adversarial Attacks on Variational Autoencoders with MCMC

Smoothed Embeddings for Certified Few-Shot Learning

Instability and Local Minima in GAN Training with Kernel Discriminators

Beyond the Return: Off-policy Function Estimation under User-specified Error-measuring Distributions

On Kernelized Multi-Armed Bandits with Constraints

Target alignment in truncated kernel ridge regression

Local Bayesian optimization via maximizing probability of descent

MEMO: Test Time Robustness via Adaptation and Augmentation

Latent Planning via Expansive Tree Search

Efficient and Effective Optimal Transport-Based Biclustering

Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networks

On the Adversarial Robustness of Mixture of Experts

Scalable Distributional Robustness in a Class of Non-Convex Optimization with Guarantees

A framework for bilevel optimization that enables stochastic and global variance reduction algorithms

Trust Region Policy Optimization with Optimal Transport Discrepancies: Duality and Algorithm for Continuous Actions

LobsDICE: Offline Learning from Observation via Stationary Distribution Correction Estimation

A Stochastic Linearized Augmented Lagrangian Method for Decentralized Bilevel Optimization

Amortized Proximal Optimization

Batch Bayesian Optimization on Permutations using the Acquisition Weighted Kernel

On the difficulty of learning chaotic dynamics with RNNs

Learning to Configure Computer Networks with Neural Algorithmic Reasoning

Autoregressive Search Engines: Generating Substrings as Document Identifiers

Efficient learning of nonlinear prediction models with time-series privileged information

Revisiting Active Sets for Gaussian Process Decoders

Tractable Function-Space Variational Inference in Bayesian Neural Networks

RNNs of RNNs: Recursive Construction of Stable Assemblies of Recurrent Neural Networks

Use-Case-Grounded Simulations for Explanation Evaluation

Autoformalization with Large Language Models

VCT: A Video Compression Transformer

Diffusion Curvature for Estimating Local Curvature in High Dimensional Data

Linear tree shap

Kernel Interpolation with Sparse Grids

Adaptive Interest for Emphatic Reinforcement Learning

Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems

Towards Improving Calibration in Object Detection Under Domain Shift

ELIGN: Expectation Alignment as a Multi-Agent Intrinsic Reward

Model-Based Imitation Learning for Urban Driving

Repairing Neural Networks by Leaving the Right Past Behind

Meta-Reinforcement Learning with Self-Modifying Networks

The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning

NeuForm: Adaptive Overfitting for Neural Shape Editing

Semantic uncertainty intervals for disentangled latent spaces

Increasing the Scope as You Learn: Adaptive Bayesian Optimization in Nested Subspaces

First Hitting Diffusion Models for Generating Manifold, Graph and Categorical Data

On Convergence of FedProx: Local Dissimilarity Invariant Bounds, Non-smoothness and Beyond

Multi-Objective Deep Learning with Adaptive Reference Vectors

The Nature of Temporal Difference Errors in Multi-step Distributional Reinforcement Learning

Envy-free Policy Teaching to Multiple Agents

When are Local Queries Useful for Robust Learning?

Generalization for multiclass classification with overparameterized linear models

Statistical Learning and Inverse Problems: A Stochastic Gradient Approach

Algorithms that Approximate Data Removal: New Results and Limitations

Batch-Size Independent Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms or Independent Arms

Efficient Phi-Regret Minimization in Extensive-Form Games via Online Mirror Descent

Reinforcement Learning in a Birth and Death Process: Breaking the Dependence on the State Space

Provably Efficient Model-Free Constrained RL with Linear Function Approximation

Convergence for score-based generative modeling with polynomial complexity

Efficient Dataset Distillation using Random Feature Approximation

The Effects of Regularization and Data Augmentation are Class Dependent

EpiGRAF: Rethinking training of 3D GANs

Insights into Pre-training via Simpler Synthetic Tasks

GPT3.int8(): 8-bit Matrix Multiplication for Transformers at Scale

STNDT: Modeling Neural Population Activity with Spatiotemporal Transformers

Neural Shape Deformation Priors

SPoVT: Semantic-Prototype Variational Transformer for Dense Point Cloud Semantic Completion

Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone

Beyond Not-Forgetting: Continual Learning with Backward Knowledge Transfer

SKFlow: Learning Optical Flow with Super Kernels

Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Tasks

Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative

3D Concept Grounding on Neural Fields

Bridge the Gap Between Architecture Spaces via A Cross-Domain Predictor

Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation

Uncertainty-Aware Hierarchical Refinement for Incremental Implicitly-Refined Classification

PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds

ShapeCrafter: A Recursive Text-Conditioned 3D Shape Generation Model

On the Learning Mechanisms in Physical Reasoning

Benign, Tempered, or Catastrophic: Toward a Refined Taxonomy of Overfitting

The trade-offs of model size in large recommendation models : 100GB to 10MB Criteo-tb DLRM model

Geodesic Graph Neural Network for Efficient Graph Representation Learning

Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited

SignRFF: Sign Random Fourier Features

Rapidly Mixing Multiple-try Metropolis Algorithms for Model Selection Problems

What is a Good Metric to Study Generalization of Minimax Learners?

Non-stationary Bandits with Knapsacks

Semi-Supervised Learning with Decision Trees: Graph Laplacian Tree Alternating Optimization

Learning on Arbitrary Graph Topologies via Predictive Coding

Asynchronous Actor-Critic for Multi-Agent Reinforcement Learning

Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos

Patching open-vocabulary models by interpolating weights

Generative Visual Prompt: Unifying Distributional Control of Pre-Trained Generative Models

Learning Options via Compression

On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learning

Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress

Rethinking Generalization in Few-Shot Classification

ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Model

Deep Fourier Up-Sampling

Provable Subspace Identification Under Post-Nonlinear Mixtures

Distributed Distributionally Robust Optimization with Non-Convex Objectives

GhostNetV2: Enhance Cheap Operation with Long-Range Attention

Exploiting Semantic Relations for Glass Surface Detection

A Simple Approach to Automated Spectral Clustering

Hiding Images in Deep Probabilistic Models

Analyzing Lottery Ticket Hypothesis from PAC-Bayesian Theory Perspective

Large Language Models are Zero-Shot Reasoners

Sym-NCO: Leveraging Symmetricity for Neural Combinatorial Optimization

Randomized Channel Shuffling: Minimal-Overhead Backdoor Attack Detection without Clean Datasets

Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active Learning

A Simple Decentralized Cross-Entropy Method

The Missing Invariance Principle found -- the Reciprocal Twin of Invariant Risk Minimization

Active Learning with Safety Constraints

A PAC-Bayesian Generalization Bound for Equivariant Networks

When to Intervene: Learning Optimal Intervention Policies for Critical Events

Recall Distortion in Neural Network Pruning and the Undecayed Pruning Algorithm

Efficient and Modular Implicit Differentiation

Detection and Localization of Changes in Conditional Distributions

Turbocharging Solution Concepts: Solving NEs, CEs and CCEs with Neural Equilibrium Solvers

DGD^2: A Linearly Convergent Distributed Algorithm For High-dimensional Statistical Recovery

Robust Streaming PCA

Trimmed Maximum Likelihood Estimation for Robust Generalized Linear Model

Sampling with Riemannian Hamiltonian Monte Carlo in a Constrained Space

Off-Policy Evaluation with Policy-Dependent Optimization Response

Bayesian Risk Markov Decision Processes

Variational inference via Wasserstein gradient flows

Alternating Mirror Descent for Constrained Min-Max Games

Efficient and Near-Optimal Smoothed Online Learning for Generalized Linear Functions

Inducing Equilibria via Incentives: Simultaneous Design-and-Play Ensures Global Convergence

Mean Estimation with User-level Privacy under Data Heterogeneity

Intrinsic dimensionality estimation using Normalizing Flows

Washing The Unwashable : On The (Im)possibility of Fairwashing Detection

Differentially Private Graph Learning via Sensitivity-Bounded Personalized PageRank

Independence Testing-Based Approach to Causal Discovery under Measurement Error and Linear Non-Gaussian Models

Explainable Reinforcement Learning via Model Transforms

Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability

Neural Circuit Architectural Priors for Embodied Control

Action-modulated midbrain dopamine activity arises from distributed control policies

When are Offline Two-Player Zero-Sum Markov Games Solvable?

Private and Communication-Efficient Algorithms for Entropy Estimation

Approximate Value Equivalence

Size and depth of monotone neural networks: interpolation and approximation

Characterization of Excess Risk for Locally Strongly Convex Population Risk

Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs

A Near-Optimal Best-of-Both-Worlds Algorithm for Online Learning with Feedback Graphs

Optimal Rates for Regularized Conditional Mean Embedding Learning

The Burer-Monteiro SDP method can fail even above the Barvinok-Pataki bound

Contextual Dynamic Pricing with Unknown Noise: Explore-then-UCB Strategy and Improved Regrets

Efficient Frameworks for Generalized Low-Rank Matrix Bandit Problems

Generic bounds on the approximation error for physics-informed (and) operator learning

Zero-Sum Stochastic Stackelberg Games

Fair and Efficient Allocations Without Obvious Manipulations

Faster Linear Algebra for Distance Matrices

SQ Lower Bounds for Learning Single Neurons with Massart Noise

A Differentially Private Linear-Time fPTAS for the Minimum Enclosing Ball Problem

Subquadratic Kronecker Regression with Applications to Tensor Decomposition

Optimal Gradient Sliding and its Application to Optimal Distributed Optimization Under Similarity

Adam Can Converge Without Any Modification On Update Rules

Oracle-Efficient Online Learning for Smoothed Adversaries

Active Learning of Classifiers with Label and Seed Queries

Near-Optimal Goal-Oriented Reinforcement Learning in Non-Stationary Environments

Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning

Improved Coresets for Euclidean $k$-Means

Sampling from Log-Concave Distributions with Infinity-Distance Guarantees

Stochastic Halpern Iteration with Variance Reduction for Stochastic Monotone Inclusions

Sequential Information Design: Learning to Persuade in the Dark

Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization

Exponential Separations in Symmetric Neural Networks

Distributional Convergence of the Sliced Wasserstein Process

Bridging Central and Local Differential Privacy in Data Acquisition Mechanisms

Unlabelled Sample Compression Schemes for Intersection-Closed Classes and Extremal Classes

On Margin Maximization in Linear and ReLU Networks

Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization

A Scalable Deterministic Global Optimization Algorithm for Training Optimal Decision Tree

Is $L^2$ Physics Informed Loss Always Suitable for Training Physics Informed Neural Network?

Recursive Reasoning in Minimax Games: A Level $k$ Gradient Play Method

Concept Activation Regions: A Generalized Framework For Concept-Based Explanations

Fair Rank Aggregation

Variance Reduced ProxSkip: Algorithm, Theory and Application to Federated Learning

Recursive Reinforcement Learning

The price of ignorance: how much does it cost to forget noise structure in low-rank matrix estimation?

PDSketch: Integrated Domain Programming, Learning, and Planning

Human-AI Shared Control via Policy Dissection

Embodied Scene-aware Human Pose Estimation

A Character-Level Length-Control Algorithm for Non-Autoregressive Sentence Summarization

E-MAPP: Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance

Semi-Supervised Generative Models for Multiagent Trajectories

Scale-invariant Learning by Physics Inversion

Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language

Are Defenses for Graph Neural Networks Robust?

Human-AI Collaborative Bayesian Optimisation

On the Interpretability of Regularisation for Neural Networks Through Model Gradient Similarity

Modular Flows: Differential Molecular Generation

Error Correction Code Transformer

BYOL-Explore: Exploration by Bootstrapped Prediction

TransBoost: Improving the Best ImageNet Performance using Deep Transduction

MorphTE: Injecting Morphology in Tensorized Embeddings

Attention-based Neural Cellular Automata

Benchopt: Reproducible, efficient and collaborative optimization benchmarks

EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL

VER: Scaling On-Policy RL Leads to the Emergence of Navigation in Embodied Rearrangement

Redistribution of Weights and Activations for AdderNet Quantization

Eliciting Thinking Hierarchy without a Prior

First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization

Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials

Identification, Amplification and Measurement: A bridge to Gaussian Differential Privacy

Dataset Distillation via Factorization

Oscillatory Tracking of Continuous Attractor Neural Networks Account for Phase Precession and Procession of Hippocampal Place Cells

Palm up: Playing in the Latent Manifold for Unsupervised Pretraining

Towards Trustworthy Automatic Diagnosis Systems by Emulating Doctors' Reasoning with Deep Reinforcement Learning

Large-Scale Retrieval for Reinforcement Learning

What Can Transformers Learn In-Context? A Case Study of Simple Function Classes

Chain of Thought Imitation with Procedure Cloning

First-Order Algorithms for Min-Max Optimization in Geodesic Metric Spaces

On the Identifiability of Nonlinear ICA: Sparsity and Beyond

Biologically-plausible backpropagation through arbitrary timespans via local neuromodulators

Nonlinear MCMC for Bayesian Machine Learning

Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture

Fast Algorithms for Packing Proportional Fairness and its Dual

Approaching Quartic Convergence Rates for Quasi-Stochastic Approximation with Application to Gradient-Free Optimization

Robust Generalized Method of Moments: A Finite Sample Viewpoint

Adapting to Online Label Shift with Provable Guarantees

Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries

Reconstruction on Trees and Low-Degree Polynomials

Benign Underfitting of Stochastic Gradient Descent

Using natural language and program abstractions to instill human inductive biases in machines

Revisiting Injective Attacks on Recommender Systems

PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies

SIXO: Smoothing Inference with Twisted Objectives

Robust Graph Structure Learning via Multiple Statistical Tests

Fairness Reprogramming

Private Graph All-Pairwise-Shortest-Path Distance Release with Improved Error Rate

Optimal Comparator Adaptive Online Learning with Switching Cost

Supervised Training of Conditional Monge Maps

Deterministic Langevin Monte Carlo with Normalizing Flows for Bayesian Inference

CGLB: Benchmark Tasks for Continual Graph Learning

ADBench: Anomaly Detection Benchmark

Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image Classification

BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs

Is one annotation enough? - A data-centric image classification benchmark for noisy and ambiguous label estimation

Dungeons and Data: A Large-Scale NetHack Dataset

Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement Learning

EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations

EgoTaskQA: Understanding Human Tasks in Egocentric Videos

SCAMPS: Synthetics for Camera Measurement of Physiological Signals

Robustness Disparities in Face Detection

Long Range Graph Benchmark

CLEVRER-Humans: Describing Physical and Causal Events the Human Way

CLiMB: A Continual Learning Benchmark for Vision-and-Language Tasks

OLIVES Dataset: Ophthalmic Labels for Investigating Visual Eye Semantics

SkinCon: A skin disease dataset densely annotated by domain experts for fine-grained debugging and analysis

Understanding Aesthetics with Language: A Photo Critique Dataset for Aesthetic Assessment

ENS-10: A Dataset For Post-Processing Ensemble Weather Forecasts

Hard ImageNet: Segmentations for Objects with Strong Spurious Cues

Video compression dataset and benchmark of learning-based video-quality metrics

TweetNERD - End to End Entity Linking Benchmark for Tweets

BigBio: A Framework for Data-Centric Biomedical Natural Language Processing

Pythae: Unifying Generative Autoencoders in Python - A Benchmarking Use Case

A Dataset for Efforts Towards Achieving the Sustainable Development Goal of Safe Working Environments

(f,Gamma)-Divergences: Interpolating between f-Divergences and Integral Probability Metrics

A Bregman Learning Framework for Sparse Neural Networks

D-GCCA: Decomposition-based Generalized Canonical Correlation Analysis for Multi-view High-dimensional Data

A Primer for Neural Arithmetic Logic Modules

[Re] Explaining in Style: Training a GAN to explain a classifier in StyleSpace

[Re] A Cluster-based Approach for Improving Isotropy in Contextual Embedding Space

[Re] Replication study of 'Data-Driven Methods for Balancing Fairness and Efficiency in Ride-Pooling'

(ends 4:00 PM)

4 p.m.

FRI 2 DEC

5:15 a.m.

Registration Desk

(ends 3:00 PM)

5:30 a.m.

Workshop:

Second Workshop on Efficient Natural Language and Speech Processing (ENLSP-II)

(ends 4:00 PM)

5:50 a.m.

Workshop:

Progress and Challenges in Building Trustworthy Embodied AI

(ends 3:00 PM)

6 a.m.

Workshop:

AI for Accelerated Materials Design (AI4Mat)

(ends 3:00 PM)

Workshop:

Synthetic Data for Empowering ML Research

(ends 3:00 PM)

Workshop:

AI for Science: Progress and Promises

(ends 4:00 PM)

6:15 a.m.

Workshop:

Order up! The Benefits of Higher-Order Optimization in Machine Learning

(ends 3:00 PM)

6:20 a.m.

Workshop:

3rd Offline Reinforcement Learning Workshop: Offline RL as a "Launchpad"

(ends 3:30 PM)

6:30 a.m.

Workshop:

Human in the Loop Learning (HiLL) Workshop at NeurIPS 2022

(ends 3:00 PM)

Workshop:

Memory in Artificial and Real Intelligence (MemARI)

(ends 3:00 PM)

Workshop:

LaReL: Language and Reinforcement Learning

(ends 3:00 PM)

Workshop:

INTERPOLATE — First Workshop on Interpolation Regularizers and Beyond

(ends 4:00 PM)

Workshop:

Causal Machine Learning for Real-World Impact

(ends 3:00 PM)

Workshop:

Table Representation Learning

(ends 3:45 PM)

Workshop:

Federated Learning: Recent Advances and New Challenges

(ends 3:00 PM)

Workshop:

Has it Trained Yet? A Workshop for Algorithmic Efficiency in Practical Neural Network Training

(ends 3:00 PM)

6:40 a.m.

Workshop:

New Frontiers in Graph Learning

(ends 3:00 PM)

6:45 a.m.

Workshop:

Shared Visual Representations in Human and Machine Intelligence (SVRHM)

(ends 4:00 PM)

6:50 a.m.

Workshop:

NeurIPS 2022 Workshop on Score-Based Methods

(ends 3:00 PM)

6:55 a.m.

Workshop:

Medical Imaging meets NeurIPS

(ends 3:00 PM)

7 a.m.

Workshop:

NeurIPS 2022 Workshop on Meta-Learning

(ends 4:00 PM)

Workshop:

Gaussian Processes, Spatiotemporal Modeling, and Decision-making Systems

(ends 4:00 PM)

Workshop:

All Things Attention: Bridging Different Perspectives on Attention

(ends 4:00 PM)

Workshop:

Robustness in Sequence Modeling

(ends 3:00 PM)

Workshop:

Learning from Time Series for Health

(ends 3:00 PM)

8 a.m.

Break:

Coffee Break

(ends 8:30 AM)

1 p.m.

Break:

Coffee Break

(ends 1:30 PM)

SAT 3 DEC

5:15 a.m.

Registration Desk

(ends 10:00 AM)

5:30 a.m.

Workshop:

Algorithmic Fairness through the Lens of Causality and Privacy

(ends 2:55 PM)

Workshop:

Gaze meets ML

(ends 3:00 PM)

Workshop:

Temporal Graph Learning Workshop

(ends 3:00 PM)

Workshop:

Reinforcement Learning for Real Life (RL4RealLife) Workshop

(ends 3:00 PM)

5:50 a.m.

Workshop:

Machine Learning and the Physical Sciences

(ends 3:00 PM)

6:15 a.m.

Workshop:

I Can’t Believe It’s Not Better: Understanding Deep Learning Through Empirical Falsification

(ends 3:00 PM)

Workshop:

Symmetry and Geometry in Neural Representations (NeurReps)

(ends 3:00 PM)

Workshop:

Self-Supervised Learning: Theory and Practice

(ends 3:00 PM)

Workshop:

The Fourth Workshop on AI for Humanitarian Assistance and Disaster Response

(ends 2:15 PM)

6:20 a.m.

Workshop:

Machine Learning for Autonomous Driving

(ends 3:00 PM)

6:30 a.m.

Workshop:

Machine Learning for Systems

(ends 2:30 PM)

Workshop:

Information-Theoretic Principles in Cognitive Systems

(ends 3:00 PM)

Workshop:

Machine Learning in Structural Biology Workshop

(ends 3:00 PM)

6:45 a.m.

Workshop:

Broadening Research Collaborations

(ends 3:00 PM)

Workshop:

Decentralization and Trustworthy Machine Learning in Web3: Methodologies, Platforms, and Applications

(ends 2:00 PM)

6:50 a.m.

Workshop:

Foundation Models for Decision Making

(ends 2:30 PM)

Workshop:

Transfer Learning for Natural Language Processing

(ends 3:00 PM)

6:55 a.m.

Workshop:

MATH-AI: Toward Human-Level Mathematical Reasoning

(ends 3:00 PM)

Workshop:

OPT 2022: Optimization for Machine Learning

(ends 2:50 PM)

7 a.m.

Workshop:

A causal view on dynamical systems

(ends 3:00 PM)

Workshop:

InterNLP: Workshop on Interactive Learning for Natural Language Processing

(ends 2:55 PM)

Workshop:

Workshop on Distribution Shifts: Connecting Methods and Applications

(ends 3:00 PM)

7:30 a.m.

Workshop:

Human Evaluation of Generative Models

(ends 2:15 PM)

8 a.m.

Break:

Coffee Break

(ends 8:30 AM)

1 p.m.

Break:

Coffee Break

(ends 1:30 PM)

MON 5 DEC

2 a.m.

Tutorial:

The Role of Meta-learning for Few-shot Learning

(ends 4:30 AM)

5 a.m.

Tutorial:

Foundational Robustness of Foundation Models

(ends 7:30 AM)

Tutorial:

Lifelong Learning Machines

(ends 7:30 AM)

6:30 a.m.

Affinity Workshop:

Women in Machine Learning - Virtual

(ends 1:00 PM)

8 a.m.

Tutorial:

Neurosymbolic Programming

(ends 10:30 AM)

Tutorial:

Probabilistic Circuits: Representations, Inference, Learning and Applications

(ends 10:30 AM)

Tutorial:

Advances in NLP and their Applications to Healthcare

(ends 10:30 AM)

11 a.m.

Tutorial:

Advances in Bayesian Optimization

(ends 1:30 PM)

Tutorial:

Incentive-Aware Machine Learning: A Tale of Robustness, Fairness, Improvement, and Performativity

(ends 1:30 PM)

Tutorial:

Algorithmic fairness: at the intersections

(ends 1:30 PM)

Affinity Poster Session:

Virtual Affinity Poster Session

(ends 1:00 PM)

2 p.m.

Tutorial:

Data Compression with Machine Learning

(ends 4:30 PM)

Tutorial:

Creative Culture and Machine Learning

(ends 4:30 PM)

5 p.m.

Tutorial:

Fair and Socially Responsible ML for Recommendations: Challenges and Perspectives

(ends 7:30 PM)

Tutorial:

Theory and Practice of Efficient and Accurate Dataset Construction

(ends 7:30 PM)

TUE 6 DEC

3 a.m.

Competition:

The MineRL BASALT Competition on Fine-tuning from Human Feedback

(ends 6:00 AM)

Competition:

Traffic4cast 2022 – Predict Dynamics along Graph Edges from Sparse Node Data: Whole City Traffic and ETA from simple Road Counters

(ends 6:30 AM)

Competition:

Cross-Domain MetaDL: Any-Way Any-Shot Learning Competition with Novel Datasets from Practical Domains

(ends 5:35 AM)

Competition:

Real Robot Challenge III - Learning Dexterous Manipulation from Offline Data in the Real World

(ends 6:00 AM)

Competition:

Causal Insights for Learning Paths in Education

(ends 6:00 AM)

Competition:

IGLU: Interactive Grounded Language Understanding in a Collaborative Environment

(ends 6:00 AM)

5 a.m.

Competition:

Driving SMARTS

(ends 7:00 AM)

9 a.m.