NeurIPS 2020 Schedule

Filter Events

SUN 6 DEC

5 a.m.

Expo Workshop:

Machine Learning at Netflix

(ends 8:00 AM)

Expo Workshop:

Building AI with Security and Privacy in mind

(ends 9:00 AM)

Expo Talk Panel:

scikit-learn and fairness, tools and challenges

(ends 6:00 AM)

Expo Talk Panel:

The challenges and latest advances in the field of causal AI

(ends 6:00 AM)

6 a.m.

Expo Talk Panel:

How we leverage machine learning and AI to develop life-changing medicines - a case study with COVID-19.

(ends 7:00 AM)

7 a.m.

Expo Talk Panel:

Accelerated Training with ML Compute on M1-Powered Macs

(ends 8:00 AM)

Expo Talk Panel:

Drifting Efficiently Through the Stratosphere Using Deep Reinforcement Learning

(ends 8:00 AM)

8 a.m.

Expo Talk Panel:

Making boats fly by scaling Reinforcement Learning with Software 2.0

(ends 9:00 AM)

9 a.m.

Expo Talk Panel:

Automating Wildlife Conservation for Cetaceans

(ends 10:00 AM)

Expo Talk Panel:

AI against COVID-19 at IBM Research

(ends 10:00 AM)

10 a.m.

Expo Workshop:

Real World RL with Vowpal Wabbit: Beyond Contextual Bandits

(ends 2:00 PM)

Expo Workshop:

Mining and Learning with Graphs at Scale

(ends 2:05 PM)

Expo Workshop:

Perspectives on Neurosymbolic Artificial Intelligence Research

(ends 1:55 PM)

Expo Talk Panel:

Fairness, Explainability, and Privacy in AI/ML Systems

(ends 11:00 AM)

11 a.m.

Expo Talk Panel:

AI4Code @ IBM and Red Hat

(ends 12:00 PM)

Expo Talk Panel:

Challenges in the adoption of Machine Learning in Health Care

(ends 12:00 PM)

noon

Expo Demonstration:

Using Sparse Quantization for Efficient Inference on Deep Neural Networks

(ends 1:00 PM)

1 p.m.

Expo Talk Panel:

Human-Centered AI @ IBM Research –Automation versus Collaboration in the Age of AI

(ends 2:00 PM)

Expo Talk Panel:

Modern ML Meets Financial Markets: Insights and Challenges

(ends 2:00 PM)

2 p.m.

Expo Talk Panel:

Building Neural Interfaces: When Real and Artificial Neurons Meet

(ends 3:00 PM)

Expo Talk Panel:

The Unpaved Path of Deploying Reliable and Human-Centered Machine Learning Systems

(ends 3:00 PM)

3 p.m.

Expo Workshop:

DAQA – Domain Adaptation and Question Answering

(ends 9:00 PM)

Expo Demonstration:

Beyond AutoML: AI Automation & Scaling

(ends 4:00 PM)

4 p.m.

Expo Talk Panel:

Scaling Data Labeling with Machine Learning

(ends 5:00 PM)

Expo Demonstration:

Medical Transcription Analysis

(ends 5:00 PM)

5 p.m.

Expo Talk Panel:

Hypotheses Generation for Applications in Biomedicine and Gastronomy

(ends 6:00 PM)

Expo Demonstration:

AWS Computer Vision Science

(ends 6:00 PM)

6 p.m.

Expo Talk Panel:

Visually Debugging ML Models With Scale Nucleus

(ends 7:00 PM)

Expo Demonstration:

Whale: Accelerate EasyTransfer training workloads within one unified distributed training framework

(ends 7:00 PM)

7 p.m.

Expo Talk Panel:

Driving New Frontiers of Machine Learning with Cruise

(ends 8:00 PM)

Expo Demonstration:

Accelerating Deep Learning for Entertainment with Sony's Neural Network Libraries and Console

(ends 8:00 PM)

8 p.m.

Expo Workshop:

New Challenges in User-Generated Content

(ends 11:59 PM)

Expo Workshop:

MachineLearningforAll-InclusiveFinance

(ends 12:00 AM)

Expo Talk Panel:

Accelerating Eye Movement Research Via Smartphone Gaze

(ends 9:00 PM)

Expo Demonstration:

The Intelligent Vision Sensor

(ends 9:00 PM)

9 p.m.

Expo Demonstration:

Discovering genetic medicines using the Deep Genomics AI Drug Discovery Platform

(ends 10:00 PM)

MON 7 DEC

midnight

Tutorial:

(Track1) Sketching and Streaming Algorithms

(ends 2:30 AM)

Tutorial:

(Track2) Deeper Conversational AI

(ends 2:30 AM)

Expo Demonstration:

GAN Applications in Fashion Article Design and Outfit Rendering

(ends 1:00 AM)

2:30 a.m.

Tutorial:

(Track1) There and Back Again: A Tale of Slopes and Expectations

(ends 5:00 AM)

Tutorial:

(Track2) Equivariant Networks

(ends 5:00 AM)

Tutorial:

(Track3) Designing Learning Dynamics

(ends 5:00 AM)

3 a.m.

Affinity Workshop:

New In ML

(ends 1:15 PM)

5:30 a.m.

Tutorial:

(Track1) Where Neuroscience meets AI (And What’s in Store for the Future)

(ends 8:00 AM)

Tutorial:

(Track2) Beyond Accuracy: Grounding Evaluation Metrics for Human-Machine Learning Systems

(ends 8:00 AM)

6 a.m.

Affinity Workshop:

Black in AI

(ends 12:30 PM)

8 a.m.

Tutorial:

(Track3) Offline Reinforcement Learning: From Algorithm Design to Practical Applications

(ends 10:30 AM)

Tutorial:

(Track2) Practical Uncertainty Estimation and Out-of-Distribution Robustness in Deep Learning

(ends 10:30 AM)

Tutorial:

(Track1) Advances in Approximate Inference

(ends 10:30 AM)

Affinity Workshop:

LXAI Research @ NeurIPS 2020

(ends 7:00 PM)

11 a.m.

Tutorial:

(Track1) Abstraction & Reasoning in AI systems: Modern Perspectives

(ends 1:30 PM)

Tutorial:

(Track2) Machine Learning for Astrophysics and Astrophysics Problems for Machine Learning

(ends 1:30 PM)

Tutorial:

(Track3) Policy Optimization in Reinforcement Learning

(ends 1:30 PM)

12:30 p.m.

Affinity Poster Session:

Joint Affinity Groups Poster Session

(ends 2:30 PM)

1:30 p.m.

Tutorial:

(Track2) Explaining Machine Learning Predictions: State-of-the-art, Challenges, and Opportunities

(ends 4:00 PM)

Tutorial:

(Track3) Deep Implicit Layers: Neural ODEs, Equilibrium Models, and Differentiable Optimization

(ends 4:00 PM)

Tutorial:

(Track1) Federated Learning and Analytics: Industry Meets Academia

(ends 4:00 PM)

5 p.m.

Invited Talk:

You Can’t Escape Hyperparameters and Latent Variables: Machine Learning as a Software Engineering Enterprise

Charles Isbell

(ends 7:00 PM)

6 p.m.

Orals & Spotlights Track 01: Representation/Relational [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Learning Physical Graph Representations from Visual Scenes

[6:15] Multi-label Contrastive Predictive Coding

[6:30] Equivariant Networks for Hierarchical Structures

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] On the Equivalence between Online and Private Learnability beyond Binary Classification

[7:10] Variational Inference for Graph Convolutional Networks in the Absence of Graph Data and Adversarial Settings

[7:20] Joint Contrastive Learning with Infinite Possibilities

[7:30] Neural Methods for Point-wise Dependency Estimation

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:30

[7:50] Design Space for Graph Neural Networks

[8:00] Debiased Contrastive Learning

[8:10] The Autoencoding Variational Autoencoder

[8:20] Unsupervised Representation Learning by Invariance Propagation

Q&A s 8:30-8:40

[8:30] Joint Q&A for Preceeding Spotlights

Break s 8:40-9:00

Break

(ends 9:00 PM)

Orals & Spotlights Track 02: COVID/Health/Bio Applications [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] When and How to Lift the Lockdown? Global COVID-19 Scenario Analysis and Policy Assessment using Compartmental Gaussian Processes

[6:15] Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement

[6:30] Neural encoding with visual attention

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] Simulating a Primary Visual Cortex at the Front of CNNs Improves Robustness to Image Perturbations

[7:10] Using noise to probe recurrent neural network structure and prune synapses

[7:20] Interpretable Sequence Learning for Covid-19 Forecasting

[7:30] Kalman Filtering Attention for User Behavior Modeling in CTR Prediction

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:20

[7:50] Demixed shared component analysis of neural population data from multiple brain areas

[8:00] Minimax Optimal Nonparametric Estimation of Heterogeneous Treatment Effects

[8:10] The Devil is in the Detail: A Framework for Macroscopic Prediction via Microscopic Models

Q&A s 8:20-8:30

[8:20] Joint Q&A for Preceeding Spotlights

Break s 8:30-9:00

Break

(ends 9:00 PM)

Orals & Spotlights Track 03: Language/Audio Applications [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Language Models are Few-Shot Learners

[6:15] Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search

[6:30] The Cone of Silence: Speech Separation by Localization

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] Unsupervised Sound Separation Using Mixture Invariant Training

[7:10] Investigating Gender Bias in Language Models Using Causal Mediation Analysis

[7:20] A Simple Language Model for Task-Oriented Dialogue

[7:30] ConvBERT: Improving BERT with Span-based Dynamic Convolution

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:30

[7:50] Cross-lingual Retrieval for Iterative Self-Supervised Training

[8:00] DynaBERT: Dynamic BERT with Adaptive Width and Depth

[8:10] Incorporating Pragmatic Reasoning Communication into Emergent Language

[8:20] De-Anonymizing Text by Fingerprinting Language Generation

Q&A s 8:30-8:40

[8:30] Joint Q&A for Preceeding Spotlights

Break s 8:40-9:00

Break

(ends 9:00 PM)

Orals & Spotlights Track 04: Reinforcement Learning [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] An Efficient Asynchronous Method for Integrating Evolutionary and Gradient-based Policy Search

[6:15] Novelty Search in Representational Space for Sample Efficient Exploration

[6:30] Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] First Order Constrained Optimization in Policy Space

[7:10] CoinDICE: Off-Policy Confidence Interval Estimation

[7:20] DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction

[7:30] Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:30

[7:50] Provably Efficient Exploration for Reinforcement Learning Using Unsupervised Learning

[8:00] Bayesian Multi-type Mean Field Multi-agent Imitation Learning

[8:10] Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity

[8:20] Safe Reinforcement Learning via Curriculum Induction

Q&A s 8:30-8:40

[8:30] Joint Q&A for Preceeding Spotlights

Break s 8:40-9:00

Break

(ends 9:00 PM)

9 p.m.

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

Rankmax: An Adaptive Projection Alternative to the Softmax Function

Field-wise Learning for Multi-field Categorical Data

Deep Diffusion-Invariant Wasserstein Distributional Classification

No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems

Efficient Clustering Based On A Unified View Of K-means And Ratio-cut

Probabilistic Fair Clustering

Sampling-Decomposable Generative Adversarial Recommender

Trading Personalization for Accuracy: Data Debugging in Collaborative Filtering

Ratio Trace Formulation of Wasserstein Discriminant Analysis

Coresets for Regressions with Panel Data

Multi-task Additive Models for Robust Estimation and Automatic Structure Discovery

Adversarial Learning for Robust Deep Clustering

Adversarial Counterfactual Learning and Evaluation for Recommender System

Adversarial Crowdsourcing Through Robust Rank-One Matrix Completion

Interventional Few-Shot Learning

Neural Methods for Point-wise Dependency Estimation

Multi-label Contrastive Predictive Coding

Self-Supervised Relationship Probing

Debiased Contrastive Learning

The Autoencoding Variational Autoencoder

Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction

Unsupervised Data Augmentation for Consistency Training

Temporal Positive-unlabeled Learning for Biomedical Hypothesis Generation via Risk Estimation

Hard Negative Mixing for Contrastive Learning

Parametric Instance Classification for Unsupervised Visual Feature learning

VIME: Extending the Success of Self- and Semi-supervised Learning to Tabular Domain

Unsupervised Representation Learning by Invariance Propagation

Joint Contrastive Learning with Infinite Possibilities

Variational Inference for Graph Convolutional Networks in the Absence of Graph Data and Adversarial Settings

Restoring Negative Information in Few-Shot Object Detection

One-sample Guided Object Representation Disassembling

Few-shot Visual Reasoning with Meta-Analogical Contrastive Learning

Latent Dynamic Factor Analysis of High-Dimensional Neural Recordings

Heavy-tailed Representations, Text Polarity Classification & Data Augmentation

Hierarchical Poset Decoding for Compositional Generalization in Language

Strongly Incremental Constituency Parsing with Graph Neural Networks

A Simple Language Model for Task-Oriented Dialogue

Learning Dynamic Belief Graphs to Generalize on Text-Based Games

Incorporating Pragmatic Reasoning Communication into Emergent Language

Learning Strategic Network Emergence Games

Fighting Copycat Agents in Behavioral Cloning from Observation Histories

Attention-Gated Brain Propagation: How the brain can implement reward-based error backpropagation

Can the Brain Do Backpropagation? --- Exact Implementation of Backpropagation in Predictive Coding Networks

Demixed shared component analysis of neural population data from multiple brain areas

Neural encoding with visual attention

On Numerosity of Deep Neural Networks

Compact task representations as a normative model for higher-order brain activity

Using noise to probe recurrent neural network structure and prune synapses

An Imitation from Observation Approach to Transfer Learning with Dynamics Mismatch

Language Models are Few-Shot Learners

Incorporating BERT into Parallel Sequence Decoding with Adapters

CogLTX: Applying BERT to Long Texts

MPNet: Masked and Permuted Pre-training for Language Understanding

MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers

Towards Neural Programming Interfaces

Language Through a Prism: A Spectral Approach for Multiscale Language Representations

ColdGANs: Taming Language GANs with Cautious Sampling Strategies

ConvBERT: Improving BERT with Span-based Dynamic Convolution

Investigating Gender Bias in Language Models Using Causal Mediation Analysis

Cross-lingual Retrieval for Iterative Self-Supervised Training

DynaBERT: Dynamic BERT with Adaptive Width and Depth

Pre-training via Paraphrasing

Dialog without Dialog Data: Learning Visual Dialog Agents from VQA Data

Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing

Big Bird: Transformers for Longer Sequences

Self-Supervised Generative Adversarial Compression

The Generalized Lasso with Nonlinear Observations and Generative Priors

Robust compressed sensing using generative models

Knowledge Distillation in Wide Neural Networks: Risk Bound, Data Efficiency and Imperfect Teacher

Fourier Spectrum Discrepancies in Deep Network Generated Images

Minimax Optimal Nonparametric Estimation of Heterogeneous Treatment Effects

Towards a Combinatorial Characterization of Bounded-Memory Learning

The Power of Comparisons for Actively Learning Linear Classifiers

Estimating decision tree learnability with polylogarithmic sample complexity

Provably Efficient Neural Estimation of Structural Equation Models: An Adversarial Approach

Matrix Inference and Estimation in Multi-Layer Models

Election Coding for Distributed Learning: Protecting SignSGD against Byzantine Attacks

Limits on Testing Structural Changes in Ising Models

A Robust Functional EM Algorithm for Incomplete Panel Count Data

Weston-Watkins Hinge Loss and Ordered Partitions

On the Equivalence between Online and Private Learnability beyond Binary Classification

Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model

A Finite-Time Analysis of Two Time-Scale Actor-Critic Methods

Reinforcement Learning for Control with Multiple Frequencies

Bridging Imagination and Reality for Model-Based Deep Reinforcement Learning

First Order Constrained Optimization in Policy Space

DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction

Natural Policy Gradient Primal-Dual Method for Constrained Markov Decision Processes

MOPO: Model-based Offline Policy Optimization

Trust the Model When It Is Confident: Masked Model-based Actor-Critic

Pipeline PSRO: A Scalable Approach for Finding Approximate Nash Equilibria in Large Games

Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity

MOReL: Model-Based Offline Reinforcement Learning

Variance-Reduced Off-Policy TDC Learning: Non-Asymptotic Convergence Analysis

Independent Policy Gradient Methods for Competitive Reinforcement Learning

Provably Good Batch Reinforcement Learning Without Great Exploration

(De)Randomized Smoothing for Certifiable Defense against Patch Attacks

Contrastive Learning with Adversarial Examples

CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection

Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search

The Cone of Silence: Speech Separation by Localization

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

Swapping Autoencoder for Deep Image Manipulation

LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-resolution and Beyond

Domain Generalization via Entropy Regularization

Self-Supervised Few-Shot Learning on Point Clouds

DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation

CLEARER: Multi-Scale Neural Architecture Search for Image Restoration

Language and Visual Entity Relationship Graph for Agent Navigation

Fast Fourier Convolution

Simulating a Primary Visual Cortex at the Front of CNNs Improves Robustness to Image Perturbations

The Devil is in the Detail: A Framework for Macroscopic Prediction via Microscopic Models

When and How to Lift the Lockdown? Global COVID-19 Scenario Analysis and Policy Assessment using Compartmental Gaussian Processes

Reinforced Molecular Optimization with Neighborhood-Controlled Grammars

Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement

MRI Banding Removal via Adversarial Training

Learning to Select Best Forecast Tasks for Clinical Outcome Prediction

Interpretable Sequence Learning for Covid-19 Forecasting

Adversarial Attacks on Deep Graph Matching

Adversarial Sparse Transformer for Time Series Forecasting

Diversity can be Transferred: Output Diversification for White- and Black-box Attacks

Input-Aware Dynamic Backdoor Attack

Understanding Global Feature Contributions With Additive Importance Measures

Improving Policy-Constrained Kidney Exchange via Pre-Screening

Learning Black-Box Attackers with Transferable Priors and Query Feedback

De-Anonymizing Text by Fingerprinting Language Generation

Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs

Design Space for Graph Neural Networks

Learning Physical Graph Representations from Visual Scenes

Equivariant Networks for Hierarchical Structures

ARMA Nets: Expanding Receptive Field for Dense Prediction

Storage Efficient and Dynamic Flexible Runtime Channel Pruning via Deep Reinforcement Learning

How to Characterize The Landscape of Overparameterized Convolutional Neural Networks

Towards Learning Convolutions from Scratch

Bayesian Attention Modules

Kalman Filtering Attention for User Behavior Modeling in CTR Prediction

Understanding and Exploring the Network with Stochastic Architectures

Neuron Merging: Compensating for Pruned Neurons

Position-based Scaled Gradient for Model Quantization and Pruning

ShiftAddNet: A Hardware-Inspired Deep Network

Pruning neural networks without any data by iteratively conserving synaptic flow

Attribution Preservation in Network Compression for Reliable Network Interpretation

Language as a Cognitive Tool to Imagine Goals in Curiosity Driven Exploration

An Efficient Asynchronous Method for Integrating Evolutionary and Gradient-based Policy Search

Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs

Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals

Cooperative Heterogeneous Deep Reinforcement Learning

The Mean-Squared Error of Double Q-Learning

Novelty Search in Representational Space for Sample Efficient Exploration

Learning Implicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning

Decentralized TD Tracking with Linear Function Approximation and its Finite-Time Analysis

Robust Multi-Agent Reinforcement Learning with Model Uncertainty

Bayesian Multi-type Mean Field Multi-agent Imitation Learning

Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design

Inverse Rational Control with Partially Observable Continuous Nonlinear Dynamics

Safe Reinforcement Learning via Curriculum Induction

On the Stability and Convergence of Robust Adversarial Reinforcement Learning: A Case Study on Linear Quadratic Systems

Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction

Off-Policy Evaluation via the Regularized Lagrangian

Dynamic Regret of Policy Optimization in Non-Stationary Environments

Constrained episodic reinforcement learning in concave-convex and knapsack settings

Off-Policy Interval Estimation with Lipschitz Value Iteration

CoinDICE: Off-Policy Confidence Interval Estimation

Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret

Reinforcement Learning with General Value Function Approximation: Provably Efficient Approach via Bounded Eluder Dimension

Task-agnostic Exploration in Reinforcement Learning

Provably Efficient Exploration for Reinforcement Learning Using Unsupervised Learning

On Function Approximation in Reinforcement Learning: Optimism in the Face of Large State Spaces

Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Loss

Minimax Value Interval for Off-Policy Evaluation and Policy Optimization

Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems

The Power of Predictions in Online Control

Information Theoretic Regret Bounds for Online Nonlinear Control

(ends 11:00 PM)

TUE 8 DEC

2 a.m.

Tutorial:

(Track2) Equivariant Networks Q&A

(ends 2:50 AM)

3 a.m.

Tutorial:

(Track1) There and Back Again: A Tale of Slopes and Expectations Q&A

(ends 3:50 AM)

5 a.m.

Invited Talk:

Feedback Control Perspectives on Learning

Jeff Shamma

(ends 7:00 AM)

6 a.m.

Demonstrations 1 [6:00-9:20]

Tue demos repeat on Wed

Demonstration s 6:00-9:20

MONICA: MObile Neural voIce Command Assistant for mobile games

tspDB: Time Series Predict DB

Probing Embedding Spaces in Deep Neural Networks

IBM Federated Learning Community Edition: An Interactive Demonstration

MolDesigner: Interactive Design of Efficacious Drugs with Deep Learning

MosAIc: Finding Artistic Connections across Culture with Conditional Image Retrieval

RetaiL: Open your own grocery store to reduce waste

PrototypeML: Visual Design of Arbitrarily Complex Neural Networks

A Knowledge Graph Reasoning Prototype

Shared Interest: Human Annotations vs. AI Saliency

(duration 3.3 hr)

Orals & Spotlights Track 05: Clustering/Ranking [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Exact Recovery of Mangled Clusters with Same-Cluster Queries

[6:15] Deep Transformation-Invariant Clustering

[6:30] Partially View-aligned Clustering

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] Simple and Scalable Sparse k-means Clustering via Feature Ranking

[7:10] Simultaneous Preference and Metric Learning from Paired Comparisons

[7:20] Learning Optimal Representations with the Decodable Information Bottleneck

[7:30] Manifold structure in graph embeddings

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:20

[7:50] Self-Supervised Learning by Cross-Modal Audio-Video Clustering

[8:00] Classification with Valid and Adaptive Coverage

[8:10] On ranking via sorting by estimated expected utility

Q&A s 8:20-8:30

[8:20] Joint Q&A for Preceeding Spotlights

Break s 8:30-9:00

Break

(ends 9:00 AM)

Orals & Spotlights Track 06: Dynamical Sys/Density/Sparsity [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Deep Energy-based Modeling of Discrete-Time Physics

[6:15] SLIP: Learning to Predict in Unknown Dynamical Systems with Long-Term Memory

[6:30] Dissecting Neural ODEs

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] Robust Density Estimation under Besov IPM Losses

[7:10] Almost Surely Stable Deep Dynamics

[7:20] Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks

[7:30] A Theoretical Framework for Target Propagation

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:30

[7:50] Training Generative Adversarial Networks by Solving Ordinary Differential Equations

[8:00] Information theoretic limits of learning a sparse rule

[8:10] Constant-Expansion Suffices for Compressed Sensing with Generative Priors

[8:20] Logarithmic Pruning is All You Need

Q&A s 8:30-8:40

[8:30] Joint Q&A for Preceeding Spotlights

Break s 8:40-9:00

Break

(ends 9:00 AM)

Orals & Spotlights Track 07: Vision Applications [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Deep Wiener Deconvolution: Wiener Meets Deep Learning for Image Deblurring

[6:15] Causal Intervention for Weakly-Supervised Semantic Segmentation

[6:30] Convolutional Generation of Textured 3D Meshes

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] DISK: Learning local features with policy gradient

[7:10] Wasserstein Distances for Stereo Disparity Estimation

[7:20] Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance

[7:30] Learning Semantic-aware Normalization for Generative Adversarial Networks

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:30

[7:50] Neural Sparse Voxel Fields

[8:00] 3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data

[8:10] Learning to Detect Objects with a 1 Megapixel Event Camera

[8:20] A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection

Q&A s 8:30-8:40

[8:30] Joint Q&A for Preceeding Spotlights

Break s 8:40-9:00

Break

(ends 9:00 AM)

Orals & Spotlights Track 08: Deep Learning [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Multiscale Deep Equilibrium Models

[6:15] On the Modularity of Hypernetworks

[6:30] Training Generative Adversarial Networks with Limited Data

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] MeshSDF: Differentiable Iso-Surface Extraction

[7:10] GAIT-prop: A biologically plausible learning rule derived from backpropagation of error

[7:20] Monotone operator equilibrium networks

[7:30] What Do Neural Networks Learn When Trained With Random Labels?

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:30

[7:50] H-Mem: Harnessing synaptic plasticity with Hebbian Memory Networks

[8:00] ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks

[8:10] The phase diagram of approximation rates for deep neural networks

[8:20] Optimal Lottery Tickets via Subset Sum: Logarithmic Over-Parameterization is Sufficient

Q&A s 8:30-8:40

[8:30] Joint Q&A for Preceeding Spotlights

Break s 8:40-9:00

Break

(ends 9:00 AM)

Orals & Spotlights Track 09: Reinforcement Learning [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Improved Sample Complexity for Incremental Autonomous Exploration in MDPs

[6:15] Escaping the Gravitational Pull of Softmax

[6:30] FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] Interferobot: aligning an optical interferometer by a reinforcement learning agent

[7:10] On Efficiency in Hierarchical Reinforcement Learning

[7:20] Finite-Time Analysis for Double Q-learning

[7:30] Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:30

[7:50] Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning

[8:00] Model-based Policy Optimization with Unsupervised Model Adaptation

[8:10] Variational Policy Gradient Method for Reinforcement Learning with General Utilities

[8:20] Sample-Efficient Reinforcement Learning of Undercomplete POMDPs

Q&A s 8:30-8:40

[8:30] Joint Q&A for Preceeding Spotlights

Break s 8:40-9:00

Break

(ends 9:00 AM)

Orals & Spotlights Track 10: Social/Privacy [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Adversarially Robust Streaming Algorithms via Differential Privacy

[6:15] Differentially Private Clustering: Tight Approximation Ratios

[6:30] Locally private non-asymptotic testing of discrete distributions is faster using interactive mechanisms

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] Multi-Robot Collision Avoidance under Uncertainty with Probabilistic Safety Barrier Certificates

[7:10] Private Identity Testing for High-Dimensional Distributions

[7:20] Permute-and-Flip: A new mechanism for differentially private selection

[7:30] Smoothed Analysis of Online and Differentially Private Learning

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:20

[7:50] Optimal Private Median Estimation under Minimal Distributional Assumptions

[8:00] Assisted Learning: A Framework for Multi-Organization Learning

[8:10] Higher-Order Certification For Randomized Smoothing

Q&A s 8:20-8:30

[8:20] Joint Q&A for Preceeding Spotlights

Break s 8:30-9:00

Break

(ends 9:00 AM)

Orals & Spotlights Track 11: Learning Theory [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium

[6:15] Efficient active learning of sparse halfspaces with arbitrary bounded noise

[6:30] Learning Parities with Neural Networks

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] The Adaptive Complexity of Maximizing a Gross Substitutes Valuation

[7:10] Hitting the High Notes: Subset Selection for Maximizing Expected Order Statistics

[7:20] A Bandit Learning Algorithm and Applications to Auction Design

[7:30] An Optimal Elimination Algorithm for Learning a Best Arm

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:40

[7:50] Second Order PAC-Bayesian Bounds for the Weighted Majority Vote

[8:00] PAC-Bayesian Bound for the Conditional Value at Risk

[8:10] Classification Under Misspecification: Halfspaces, Generalized Linear Models, and Evolvability

[8:20] Hedging in games: Faster convergence of external and swap regrets

[8:30] Online Bayesian Persuasion

Q&A s 8:40-8:50

[8:40] Joint Q&A for Preceeding Spotlights

Break s 8:50-9:00

Break

(ends 9:00 AM)

7 a.m.

Affinity Workshop:

Queer in AI Workshop @ NeurIPS 2020

(ends 12:30 PM)

7:30 a.m.

Affinity Workshop:

Muslims in ML

(ends 11:00 AM)

9 a.m.

Poster Session 2 [9:00-11:00]

Latent Template Induction with Gumbel-CRFs

Federated Principal Component Analysis

Learning Differential Equations that are Easy to Solve

Learning Rich Rankings

Self-supervised Co-Training for Video Representation Learning

Prophet Attention: Predicting Attention with Future Attention

Audeo: Audio Generation for a Silent Performance Video

Cascaded Text Generation with Markov Transformers

All Word Embeddings from One Embedding

Data Diversification: A Simple Strategy For Neural Machine Translation

Learning Sparse Prototypes for Text Generation

A Discrete Variational Recurrent Topic Model without the Reparametrization Trick

AViD Dataset: Anonymized Videos from Diverse Countries

Convolutional Tensor-Train LSTM for Spatio-Temporal Learning

End-to-End Learning and Intervention in Games

Cross-validation Confidence Intervals for Test Error

Learning Robust Decision Policies from Observational Data

Improved Sample Complexity for Incremental Autonomous Exploration in MDPs

Self-Imitation Learning via Generalized Lower Bound Q-learning

An Improved Analysis of (Variance-Reduced) Policy Gradient and Natural Policy Gradient Methods

One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL

An operator view of policy gradient methods

Robust Reinforcement Learning via Adversarial training with Langevin Dynamics

Improving Sample Complexity Bounds for (Natural) Actor-Critic Algorithms

How to Learn a Useful Critic? Model-based Action-Gradient-Estimator Policy Optimization

The Value Equivalence Principle for Model-Based Reinforcement Learning

Doubly Robust Off-Policy Value and Gradient Estimation for Deterministic Policies

Neurosymbolic Reinforcement Learning with Formally Verified Exploration

Near-Optimal Reinforcement Learning with Self-Play

Variational Policy Gradient Method for Reinforcement Learning with General Utilities

PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning

Deep Multimodal Fusion by Channel Exchanging

Learning Representations from Audio-Visual Spatial Alignment

Knowledge Augmented Deep Neural Networks for Joint Facial Expression and Action Unit Recognition

Causal Intervention for Weakly-Supervised Semantic Segmentation

Generative View Synthesis: From Single-view Semantics to Novel-view Images

Labelling unlabelled videos from scratch with multi-modal self-supervision

Unfolding the Alternating Optimization for Blind Super Resolution

Video Frame Interpolation without Temporal Priors

Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation

Color Visual Illusions: A Statistics-based Computational Model

A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection

Make One-Shot Video Object Segmentation Efficient Again

SIRI: Spatial Relation Induced Network For Spatial Description Resolution

Multi-Plane Program Induction with 3D Box Priors

RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces

Unsupervised object-centric video generation and decomposition in 3D

Dissecting Neural ODEs

On ranking via sorting by estimated expected utility

Constant-Expansion Suffices for Compressed Sensing with Generative Priors

Model Interpretability through the Lens of Computational Complexity

Agnostic

$Q$ -learning with Function Approximation in Deterministic Systems: Near-Optimal Bounds on Approximation Error and Sample Complexity

Smoothed Analysis of Online and Differentially Private Learning

Non-Convex SGD Learns Halfspaces with Adversarial Label Noise

Hardness of Learning Neural Networks with Natural Weights

Classification Under Misspecification: Halfspaces, Generalized Linear Models, and Evolvability

The Complexity of Adversarially Robust Proper Learning of Halfspaces with Agnostic Noise

The phase diagram of approximation rates for deep neural networks

A Dynamical Central Limit Theorem for Shallow Neural Networks

Learning Bounds for Risk-sensitive Learning

Agnostic Learning of a Single Neuron with Gradient Descent

Information theoretic limits of learning a sparse rule

From Finite to Countable-Armed Bandits

Optimal Best-arm Identification in Linear Bandits

Restless-UCB, an Efficient and Low-complexity Algorithm for Online Restless Bandits

Finite Continuum-Armed Bandits

Adversarial Blocking Bandits

Inference for Batched Bandits

Online Algorithm for Unsupervised Sequential Selection with Contextual Information

Adversarial Attacks on Linear Contextual Bandits

Crush Optimism with Pessimism: Structured Bandits Beyond Asymptotic Optimality

Finding All

$\epsilon$ -Good Arms in Stochastic Bandits

An Optimal Elimination Algorithm for Learning a Best Arm

Instance-wise Feature Grouping

POLY-HOOT: Monte-Carlo Planning in Continuous Space MDPs with Non-Asymptotic Analysis

Online Planning with Lookahead Policies

Escaping the Gravitational Pull of Softmax

Online Bayesian Persuasion

KFC: A Scalable Approximation Algorithm for

$k$ −center Fair Clustering

CoinPress: Practical Private Mean and Covariance Estimation

Auditing Differentially Private Machine Learning: How Private is Private SGD?

Private Learning of Halfspaces: Simplifying the Construction and Reducing the Sample Complexity

Smoothly Bounding User Contributions in Differential Privacy

Learning from Mixtures of Private and Public Populations

A Computational Separation between Private Learning and Online Learning

Instance-optimality in differential privacy via approximate inverse sensitivity mechanisms

Improving Sparse Vector Technique with Renyi Differential Privacy

GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators

Private Identity Testing for High-Dimensional Distributions

Optimal Private Median Estimation under Minimal Distributional Assumptions

Learning discrete distributions: user vs item-level privacy

Locally private non-asymptotic testing of discrete distributions is faster using interactive mechanisms

Mitigating Manipulation in Peer Review via Randomized Reviewer Assignments

Phase retrieval in high dimensions: Statistical and computational phase transitions

Higher-Order Spectral Clustering of Directed Graphs

Deep Transformation-Invariant Clustering

Faster DBSCAN via subsampled similarity queries

From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clustering

Strongly local p-norm-cut algorithms for semi-supervised learning and local graph clustering

Exact Recovery of Mangled Clusters with Same-Cluster Queries

Simple and Scalable Sparse k-means Clustering via Feature Ranking

Efficient Clustering for Stretched Mixtures: Landscape and Optimality

Community detection in sparse time-evolving graphs with a dynamical Bethe-Hessian

Classification with Valid and Adaptive Coverage

Self-Supervised Learning by Cross-Modal Audio-Video Clustering

HyNet: Learning Local Descriptor with Hybrid Similarity Measure and Triplet Loss

Distributionally Robust Local Non-parametric Conditional Estimation

Differentially Private Clustering: Tight Approximation Ratios

Faster Differentially Private Samplers via Rényi Divergence Analysis of Discretized Langevin MCMC

Learning to Decode: Reinforcement Learning for Decoding of Sparse Graph-Based Channel Codes

Non-Euclidean Universal Approximation

WoodFisher: Efficient Second-Order Approximation for Neural Network Compression

Deep Transformers with Latent Depth

Movement Pruning: Adaptive Sparsity by Fine-Tuning

Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot

Pruning Filter in Filter

The Lottery Ticket Hypothesis for Pre-trained BERT Networks

The Generalization-Stability Tradeoff In Neural Network Pruning

Greedy Optimization Provably Wins the Lottery: Logarithmic Number of Winning Tickets is Enough

Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks

HYDRA: Pruning Adversarially Robust Neural Networks

Logarithmic Pruning is All You Need

Optimal Lottery Tickets via Subset Sum: Logarithmic Over-Parameterization is Sufficient

Higher-Order Certification For Randomized Smoothing

Adversarial robustness via robust low rank representations

Denoised Smoothing: A Provable Defense for Pretrained Classifiers

Margins are Insufficient for Explaining Gradient Boosting

On the Power of Louvain in the Stochastic Block Model

Robust large-margin learning in hyperbolic space

Self-Learning Transformations for Improving Gaze and Head Redirection

Exactly Computing the Local Lipschitz Constant of ReLU Networks

Optimizing Mode Connectivity via Neuron Alignment

An Efficient Framework for Clustered Federated Learning

On the distance between two neural networks and the stability of learning

One Ring to Rule Them All: Certifiably Robust Geometric Perception with Outliers

Multi-Robot Collision Avoidance under Uncertainty with Probabilistic Safety Barrier Certificates

Consequences of Misaligned AI

Certified Defense to Image Transformations via Randomized Smoothing

Certifying Strategyproof Auction Networks

Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming

Improving robustness against common corruptions by covariate shift adaptation

Deeply Learned Spectral Total Variation Decomposition

Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty

Multiscale Deep Equilibrium Models

Faithful Embeddings for Knowledge Base Queries

GradAug: A New Regularization Method for Deep Neural Networks

Monotone operator equilibrium networks

Hierarchical nucleation in deep neural networks

What Do Neural Networks Learn When Trained With Random Labels?

H-Mem: Harnessing synaptic plasticity with Hebbian Memory Networks

ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks

Throughput-Optimal Topology Design for Cross-Silo Federated Learning

Wavelet Flow: Fast Training of High Resolution Normalizing Flows

Woodbury Transformations for Deep Generative Flows

Why Normalizing Flows Fail to Detect Out-of-Distribution Data

The Convex Relaxation Barrier, Revisited: Tightened Single-Neuron Relaxations for Neural Network Verification

Regret in Online Recommendation Systems

Simplify and Robustify Negative Sampling for Implicit Collaborative Filtering

Myersonian Regression

On Convergence of Nearest Neighbor Classifiers over Feature Transformations

Learning Utilities and Equilibria in Non-Truthful Auctions

Contextual Reserve Price Optimization in Auctions via Mixed Integer Programming

Secretary and Online Matching Problems with Machine Learned Advice

On the Error Resistance of Hinge-Loss Minimization

Polynomial-Time Computation of Optimal Correlated Equilibria in Two-Player Extensive-Form Games with Public Chance Moves and Beyond

Chaos, Extremism and Optimism: Volume Analysis of Learning in Games

A Game-Theoretic Analysis of the Empirical Revenue Maximization Algorithm with Endogenous Sampling

A Bandit Learning Algorithm and Applications to Auction Design

No-regret Learning in Price Competitions under Consumer Reference Effects

Robust and Heavy-Tailed Mean Estimation Made Simple, via Regret Minimization

Partially View-aligned Clustering

MeshSDF: Differentiable Iso-Surface Extraction

Joint Policy Search for Multi-agent Collaboration with Imperfect Information

On Infinite-Width Hypernetworks

Training Generative Adversarial Networks with Limited Data

Reinforcement Learning with Combinatorial Actions: An Application to Vehicle Routing

A Self-Tuning Actor-Critic Algorithm

Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis

See, Hear, Explore: Curiosity via Audio-Visual Association

Finite-Time Analysis for Double Q-learning

Adaptive Discretization for Model-Based Reinforcement Learning

Object Goal Navigation using Goal-Oriented Semantic Exploration

Online Algorithms for Multi-shop Ski Rental with Machine Learned Advice

Planning in Markov Decision Processes with Gap-Dependent Sample Complexity

A new convergent variant of Q-learning with linear function approximation

A Unified Switching System Perspective and Convergence Analysis of Q-Learning Algorithms

Adversarially Robust Streaming Algorithms via Differential Privacy

Generalized Boosting

A Topological Filter for Learning with Label Noise

Learning by Minimizing the Sum of Ranked Range

Partial Optimal Transport with applications on Positive-Unlabeled Learning

Assisted Learning: A Framework for Multi-Organization Learning

Learning Disentangled Representations and Group Structure of Dynamical Environments

Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Improving Natural Language Processing Tasks with Human Gaze-Guided Neural Attention

COBE: Contextualized Object Embeddings from Narrated Instructional Video

Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs

Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation

Can Q-Learning with Graph Networks Learn a Generalizable Branching Heuristic for a SAT Solver?

Probably Approximately Correct Constrained Learning

Sharp uniform convergence bounds through empirical centralization

Interpolation Technique to Speed Up Gradients Propagation in Neural ODEs

Gaussian Gated Linear Networks

BayReL: Bayesian Relational Learning for Multi-omics Data Integration

Manifold structure in graph embeddings

GAIT-prop: A biologically plausible learning rule derived from backpropagation of error

Learning to Learn with Feedback and Local Plasticity

A Theoretical Framework for Target Propagation

Inductive Quantum Embedding

Optimizing Neural Networks via Koopman Operator Theory

Biological credit assignment through dynamic inversion of feedforward networks

On 1/n neural representation and robustness

Real World Games Look Like Spinning Tops

Quantitative Propagation of Chaos for SGD in Wide Neural Networks

Network size and size of the weights in memorization with two-layers neural networks

Consistent Estimation of Identifiable Nonparametric Mixture Models from Grouped Observations

All-or-nothing statistical and computational phase transitions in sparse spiked matrix estimation

Soft Contrastive Learning for Visual Localization

A Flexible Framework for Designing Trainable Priors with Adaptive Smoothing and Game Encoding

Human Parsing Based Texture Transfer from Single Image to 3D Human via Cross-View Consistency

Cross-Scale Internal Graph Neural Network for Image Super-Resolution

GPS-Net: Graph-based Photometric Stereo Network

Convolutional Generation of Textured 3D Meshes

Beta R-CNN: Looking into Pedestrian Detection from Another Perspective

Neural Sparse Representation for Image Restoration

GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis

Watch out! Motion is Blurring the Vision of Your Deep Neural Networks

Continuous Object Representation Networks: Novel View Synthesis without Target View Supervision

Learning Semantic-aware Normalization for Generative Adversarial Networks

3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data

Learning to Detect Objects with a 1 Megapixel Event Camera

A Loss Function for Generative Neural Networks Based on Watson’s Perceptual Model

GANSpace: Discovering Interpretable GAN Controls

Deep Energy-based Modeling of Discrete-Time Physics

SLIP: Learning to Predict in Unknown Dynamical Systems with Long-Term Memory

Weak Form Generalized Hamiltonian Learning

Disentangling by Subspace Diffusion

Simultaneous Preference and Metric Learning from Paired Comparisons

Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks

Hold me tight! Influence of discriminative features on deep network boundaries

Training Generative Adversarial Networks by Solving Ordinary Differential Equations

Sparse Graphical Memory for Robust Planning

Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes

Bayesian Robust Optimization for Imitation Learning

Learning Parities with Neural Networks

Learning the Linear Quadratic Regulator from Nonlinear Observations

Optimal Robustness-Consistency Trade-offs for Learning-Augmented Online Algorithms

Stateful Posted Pricing with Vanishing Regret via Dynamic Deterministic Markov Decision Processes

On the Theory of Transfer Learning: The Importance of Task Diversity

Online Agnostic Boosting via Regret Minimization

Minimax Classification with 0-1 Loss and Performance Guarantees

Robust Density Estimation under Besov IPM Losses

Online Multitask Learning with Long-Term Memory

Improving Local Identifiability in Probabilistic Box Embeddings

Finite-Sample Analysis of Contractive Stochastic Approximation Using Smooth Convex Envelopes

Synthetic Data Generators -- Sequential and Private

Near-Optimal SQ Lower Bounds for Agnostically Learning Halfspaces and ReLUs under Gaussian Marginals

Statistical-Query Lower Bounds via Functional Gradients

PAC-Bayes Learning Bounds for Sample-Dependent Priors

Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms

Decision trees as partitioning machines to characterize their generalization properties

A Limitation of the PAC-Bayes Framework

Conditioning and Processing: Techniques to Improve Information-Theoretic Generalization Bounds

Second Order PAC-Bayesian Bounds for the Weighted Majority Vote

PAC-Bayes Analysis Beyond the Usual Bounds

Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness

Probabilistic Orientation Estimation with Matrix Fisher Distributions

Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation

Inference Stage Optimization for Cross-scenario 3D Human Pose Estimation

Deep Wiener Deconvolution: Wiener Meets Deep Learning for Image Deblurring

Calibrating CNNs for Lifelong Learning

Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect

Diverse Image Captioning with Context-Object Split Latent Spaces

An Analysis of SVD for Deep Rotation Estimation

DISK: Learning local features with policy gradient

Wasserstein Distances for Stereo Disparity Estimation

GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network

On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law

A Dictionary Approach to Domain-Invariant Learning in Deep Networks

Balanced Meta-Softmax for Long-Tailed Visual Recognition

Evidential Sparsification of Multimodal Latent Spaces in Conditional Variational Autoencoders

Sparse Symplectically Integrated Neural Networks

Node Embeddings and Exact Low-Rank Representations of Complex Networks

Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology

Towards Understanding Hierarchical Learning: Benefits of Neural Representations

Stochasticity of Deterministic Gradient Descent: Large Learning Rate for Multiscale Objective Function

Stochastic Gradient Descent in Correlated Settings: A Study on Gaussian Processes

Penalized Langevin dynamics with vanishing penalty for smooth and log-concave targets

Universal guarantees for decision tree induction via a higher-order splitting criterion

Learning Restricted Boltzmann Machines with Sparse Latent Variables

The Adaptive Complexity of Maximizing a Gross Substitutes Valuation

Hedging in games: Faster convergence of external and swap regrets

Nonasymptotic Guarantees for Spiked Matrix Recovery with Generative Priors

In search of robust measures of generalization

On Convergence and Generalization of Dropout Training

Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification

Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval

Correspondence learning via linearly-invariant embedding

PIE-NET: Parametric Inference of Point Cloud Edges

Neural Non-Rigid Tracking

Continuous Surface Embeddings

Learning to Orient Surfaces by Self-supervised Spherical CNNs

SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images

Neural Unsigned Distance Fields for Implicit Function Learning

Skeleton-bridged Point Completion: From Global Inference to Local Adjustment

Rotation-Invariant Local-to-Global Representation Learning for 3D Point Cloud

Deep Shells: Unsupervised Shape Correspondence with Optimal Transport

Dense Correspondences between Human Bodies via Learning Transformation Synchronization on Graphs

3D Shape Reconstruction from Vision and Touch

Canonical 3D Deformer Maps: Unifying parametric and non-parametric methods for dense weakly-supervised category reconstruction

Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance

Neural Sparse Voxel Fields

RepPoints v2: Verification Meets Regression for Object Detection

Efficient Contextual Bandits with Continuous Actions

Collapsing Bandits and Their Application to Public Health Intervention

Learning to Play Sequential Games versus Unknown Opponents

Interferobot: aligning an optical interferometer by a reinforcement learning agent

Reinforcement Learning in Factored MDPs: Oracle-Efficient Algorithms and Tighter Regret Bounds for the Non-Episodic Setting

Reinforcement Learning with Feedback Graphs

A Unifying View of Optimism in Episodic Reinforcement Learning

Provably Efficient Reward-Agnostic Navigation with Linear Value Iteration

On Reward-Free Reinforcement Learning with Linear Function Approximation

On Efficiency in Hierarchical Reinforcement Learning

Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes

Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning

Belief-Dependent Macro-Action Discovery in POMDPs using the Value of Information

High-Throughput Synchronous Deep RL

AttendLight: Universal Attention-Based Reinforcement Learning Model for Traffic Signal Control

Dynamic Submodular Maximization

Adaptive Shrinkage Estimation for Streaming Graphs

Near-Optimal Comparison Based Clustering

Impossibility Results for Grammar-Compressed Linear Algebra

Statistical control for spatio-temporal MEG/EEG source imaging with desparsified mutli-task Lasso

Submodular Meta-Learning

Fairness in Streaming Submodular Maximization: Algorithms and Hardness

Fast Adaptive Non-Monotone Submodular Maximization Subject to a Knapsack Constraint

Direct Policy Gradients: Direct Optimization of Policies in Discrete Action Spaces

Efficient active learning of sparse halfspaces with arbitrary bounded noise

Learning Structured Distributions From Untrusted Batches: Faster and Simpler

Outlier Robust Mean Estimation with Subgaussian Rates via Stability

Fictitious Play for Mean Field Games: Continuous Time Analysis and Applications

Hitting the High Notes: Subset Selection for Maximizing Expected Order Statistics

PAC-Bayesian Bound for the Conditional Value at Risk

Universal Function Approximation on Graphs

Model Class Reliance for Random Forests

Hypersolvers: Toward Fast Continuous-Depth Models

Almost Surely Stable Deep Dynamics

Learning Optimal Representations with the Decodable Information Bottleneck

Provable Online CP/PARAFAC Decomposition of a Structured Tensor via Dictionary Learning

Measuring Systematic Generalization in Neural Proof Generation with Transformers

Online Decision Based Visual Tracking via Reinforcement Learning

On the Modularity of Hypernetworks

Pushing the Limits of Narrow Precision Inferencing at Cloud Scale with Microsoft Floating Point

Counterexample-Guided Learning of Monotonic Neural Networks

Permute-and-Flip: A new mechanism for differentially private selection

No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium

Spike and slab variational Bayes for high dimensional logistic regression

How does Weight Correlation Affect Generalisation Ability of Deep Neural Networks?

Learning discrete distributions with infinite support

Off-policy Policy Evaluation For Sequential Decisions Under Unobserved Confounding

A Maximum-Entropy Approach to Off-Policy Evaluation in Average-Reward MDPs

Instance-based Generalization in Reinforcement Learning

Efficient Planning in Large MDPs with Weak Linear Function Approximation

Multi-agent active perception with prediction rewards

Gamma-Models: Generative Temporal Difference Learning for Infinite-Horizon Prediction

The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning

Expert-Supervised Reinforcement Learning for Offline Policy Learning and Evaluation

Model-based Policy Optimization with Unsupervised Model Adaptation

Deep Reinforcement and InfoMax Learning

Zap Q-Learning With Nonlinear Function Approximation

MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning

Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model

FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs

Sample-Efficient Reinforcement Learning of Undercomplete POMDPs

Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits

Self-Supervised MultiModal Versatile Networks

Deep Subspace Clustering with Data Augmentation

Learning Retrospective Knowledge with Reverse Reinforcement Learning

The MAGICAL Benchmark for Robust Imitation

Sample Efficient Reinforcement Learning via Low-Rank Matrix Estimation

Counterfactual Data Augmentation using Locally Factored Dynamics

POMDPs in Continuous Time and Discrete Spaces

Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors

Forethought and Hindsight in Credit Assignment

Learning Multi-Agent Communication through Structured Attentive Reasoning

MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation

Influence-Augmented Online Planning for Complex Environments

Security Analysis of Safe and Seldonian Reinforcement Learning Algorithms

Provably Efficient Neural GTD for Off-Policy Learning

An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay

Comparator-Adaptive Convex Bandits

(ends 11:00 AM)

noon

Symposium:

COVID-19 Symposium Day 1

(ends 4:00 PM)

Tutorial:

(Track3) Offline Reinforcement Learning: From Algorithm Design to Practical Applications Q&A

(ends 12:50 PM)

1 p.m.

Tutorial:

(Track1) Sketching and Streaming Algorithms Q&A

(ends 1:50 PM)

2 p.m.

Tutorial:

(Track2) Beyond Accuracy: Grounding Evaluation Metrics for Human-Machine Learning Systems Q&A

(ends 2:50 PM)

5 p.m.

Invited Talk:

Robustness, Verification, Privacy: Addressing Machine Learning Adversaries

Shafi Goldwasser

(ends 7:00 PM)

6 p.m.

Orals & Spotlights Track 12: Vision Applications [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Space-Time Correspondence as a Contrastive Random Walk

[6:15] Rethinking Pre-training and Self-training

[6:30] Do Adversarially Robust ImageNet Models Transfer Better?

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] Self-Supervised Visual Representation Learning from Hierarchical Grouping

[7:10] Learning Affordance Landscapes for Interaction Exploration in 3D Environments

[7:20] Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D

[7:30] Large-Scale Adversarial Training for Vision-and-Language Representation Learning

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:20

[7:50] Measuring Robustness to Natural Distribution Shifts in Image Classification

[8:00] Curriculum By Smoothing

[8:10] Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies

Q&A s 8:20-8:30

[8:20] Joint Q&A for Preceeding Spotlights

Break s 8:30-9:00

Break

(ends 9:00 PM)

Demonstrations 2 [6:00-9:20]

Tue demos repeat on Wed

Demonstration s 6:00-9:20

LMdiff: A Visual Diff Tool to Compare LanguageModels

AI Assisted Data Labeling

Automated dataset extraction from SEC filings

Generating Novelty in Open-World Multi-Agent Strategic Board Games

Fast and Automatic Visual Label Conflict Resolution

DeepRacing AI - Autonomous Motorsport Racing

ColliFlow: A Library for Executing Collaborative Intelligence Graphs

Musical Speech: A Transformer-based Composition Tool

xLP: Explainable Link Prediction Demo

Coreference Resolution for Neutralizing Gendered Pronouns

(duration 3.3 hr)

Orals & Spotlights Track 13: Deep Learning/Theory [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Implicit Neural Representations with Periodic Activation Functions

[6:15] Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation

[6:30] Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures

[7:10] Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization

[7:20] Compositional Visual Generation with Energy Based Models

[7:30] Certified Monotonic Neural Networks

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:30

[7:50] Robust Sub-Gaussian Principal Component Analysis and Width-Independent Schatten Packing

[8:00] On Correctness of Automatic Differentiation for Non-Differentiable Functions

[8:10] The Complete Lasso Tradeoff Diagram

[8:20] Quantifying the Empirical Wasserstein Distance to a Set of Measures: Beating the Curse of Dimensionality

Q&A s 8:30-8:40

[8:30] Joint Q&A for Preceeding Spotlights

Break s 8:40-9:00

Break

(ends 9:00 PM)

Orals & Spotlights Track 14: Reinforcement Learning [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement

[6:15] Learning Individually Inferred Communication for Multi-Agent Cooperation

[6:30] Can Temporal-Diﬀerence and Q-Learning Learn Representation? A Mean-Field Theory

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] Reinforcement Learning with Augmented Data

[7:10] Sub-sampling for Efficient Non-Parametric Bandit Exploration

[7:20] Language-Conditioned Imitation Learning for Robot Manipulation Tasks

[7:30] High-Dimensional Contextual Policy Search with Unknown Context Rewards using Bayesian Optimization

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:30

[7:50] Policy Improvement via Imitation of Multiple Oracles

[8:00] Generating Adjacency-Constrained Subgoals in Hierarchical Reinforcement Learning

[8:10] Avoiding Side Effects in Complex Environments

[8:20] Preference-based Reinforcement Learning with Finite-Time Guarantees

Q&A s 8:30-8:40

[8:30] Joint Q&A for Preceeding Spotlights

Break s 8:40-9:00

Break

(ends 9:00 PM)

9 p.m.

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

Conservative Q-Learning for Offline Reinforcement Learning

Towards Playing Full MOBA Games with Deep Reinforcement Learning

Federated Bayesian Optimization via Thompson Sampling

Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games

Reinforcement Learning with Augmented Data

Generating Adjacency-Constrained Subgoals in Hierarchical Reinforcement Learning

Almost Optimal Model-Free Reinforcement Learningvia Reference-Advantage Decomposition

Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

Succinct and Robust Multi-Agent Communication With Temporal Message Control

Scalable Multi-Agent Reinforcement Learning for Networked Systems with Average Reward

Learning Individually Inferred Communication for Multi-Agent Cooperation

Emergent Reciprocity and Team Formation from Randomized Uncertain Social Preferences

Marginal Utility for Planning in Continuous or Large Discrete Action Spaces

A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances

Softmax Deep Double Deterministic Policy Gradients

Non-Crossing Quantile Regression for Distributional Reinforcement Learning

Improving Generalization in Reinforcement Learning with Mixture Regularization

Choice Bandits

Differentiable Meta-Learning of Bandit Policies

Latent Bandits Revisited

Finite-Time Analysis of Round-Robin Kullback-Leibler Upper Confidence Bounds for Optimal Adaptive Allocation with Multiple Plays and Markovian Rewards

Sub-sampling for Efficient Non-Parametric Bandit Exploration

Online Learning in Contextual Bandits using Gated Linear Networks

High-Dimensional Contextual Policy Search with Unknown Context Rewards using Bayesian Optimization

Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement

$^2$ : Reward Decomposition with Representation Decomposition

Efficient Exploration of Reward Functions in Inverse Reinforcement Learning via Bayesian Optimization

Learning Guidance Rewards with Trajectory-space Smoothing

Avoiding Side Effects in Complex Environments

Reward-rational (implicit) choice: A unifying formalism for reward learning

Planning with General Objective Functions: Going Beyond Total Rewards

Preference-based Reinforcement Learning with Finite-Time Guarantees

Is Long Horizon RL More Difficult Than Short Horizon RL?

Online Meta-Critic Learning for Off-Policy Actor-Critic Methods

POMO: Policy Optimization with Multiple Optima for Reinforcement Learning

Error Bounds of Imitating Policies and Environments

Model-based Adversarial Meta-Reinforcement Learning

Offline Imitation Learning with a Misspecified Simulator

Policy Improvement via Imitation of Multiple Oracles

Toward the Fundamental Limits of Imitation Learning

Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning

Can Temporal-Diﬀerence and Q-Learning Learn Representation? A Mean-Field Theory

Multi-task Batch Reinforcement Learning with Metric Learning

Multi-Task Reinforcement Learning with Soft Modularization

Generalized Hindsight for Reinforcement Learning

Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning

BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning

Steady State Analysis of Episodic Reinforcement Learning

The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes

Learning Disentangled Representations of Videos with Missing Data

Cycle-Contrast for Self-Supervised Video Representation Learning

Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies

Blind Video Temporal Consistency via Deep Video Prior

Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Sample

Space-Time Correspondence as a Contrastive Random Walk

Do Adversarially Robust ImageNet Models Transfer Better?

Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement

Counterfactual Contrastive Learning for Weakly-Supervised Vision-Language Grounding

Forget About the LiDAR: Self-Supervised Depth Estimators with MED Probability Volumes

COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning

Stochastic Normalization

Curriculum By Smoothing

Focus of Attention Improves Information Transfer in Visual Features

Semantic Visual Navigation by Watching YouTube Videos

Lipschitz-Certifiable Training with a Tight Outer Bound

Efficient Exact Verification of Binarized Neural Networks

Information Theoretic Counterfactual Learning from Missing-Not-At-Random Feedback

CASTLE: Regularization via Auxiliary Causal Graph Discovery

Multi-Stage Influence Function

On Completeness-aware Concept-Based Explanations in Deep Neural Networks

Adaptive Online Estimation of Piecewise Polynomial Trends

Robust Optimization for Fairness with Noisy Protected Groups

Beyond Individualized Recourse: Interpretable and Interactive Summaries of Actionable Recourses

The Discrete Gaussian for Differential Privacy

Locally Differentially Private (Contextual) Bandits Learning

A Scalable Approach for Privacy-Preserving Collaborative Machine Learning

Privacy Amplification via Random Check-Ins

The Flajolet-Martin Sketch Itself Preserves Differential Privacy: Private Counting with Minimal Space

Breaking the Communication-Privacy-Accuracy Trilemma

Towards practical differentially private causal graph discovery

Optimal and Practical Algorithms for Smooth and Strongly Convex Decentralized Optimization

Relative gradient optimization of the Jacobian term in unsupervised deep learning

Multipole Graph Neural Operator for Parametric Partial Differential Equations

Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration

Proximity Operator of the Matrix Perspective Function and its Applications

Improved Algorithms for Convex-Concave Minimax Optimization

Decentralized Accelerated Proximal Gradient Descent

Optimal Epoch Stochastic Gradient Descent Ascent Methods for Min-Max Optimization

Lower Bounds and Optimal Algorithms for Personalized Federated Learning

A Scalable MIP-based Method for Learning Optimal Multivariate Decision Trees

A Feasible Level Proximal Point Method for Nonconvex Sparse Constrained Optimization

Subgroup-based Rank-1 Lattice Quasi-Monte Carlo

Efficient Nonmyopic Bayesian Optimization via One-Shot Multi-Step Trees

Optimal Query Complexity of Secure Stochastic Convex Optimization

Approximate Cross-Validation with Low-Rank Data in High Dimensions

Revisiting the Sample Complexity of Sparse Spectrum Approximation of Gaussian Processes

A Closer Look at Accuracy vs. Robustness

Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks

AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing Flows

Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free

Adversarial Distributional Training for Robust Deep Learning

On the Trade-off between Adversarial and Backdoor Robustness

An Efficient Adversarial Attack for Tree Ensembles

Adversarial Self-Supervised Contrastive Learning

Adversarial Weight Perturbation Helps Robust Generalization

Large-Scale Adversarial Training for Vision-and-Language Representation Learning

GreedyFool: Distortion-Aware Sparse Adversarial Attack

Consistency Regularization for Certified Robustness of Smoothed Classifiers

Measuring Robustness to Natural Distribution Shifts in Image Classification

Certified Monotonic Neural Networks

Backpropagating Linearly Improves Transferability of Adversarial Examples

Practical No-box Adversarial Attacks against DNNs

Learning to Adapt to Evolving Domains

MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures

Heuristic Domain Adaptation

Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation

Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization

Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID

Implicit Neural Representations with Periodic Activation Functions

Rethinking Pre-training and Self-training

MetaSDF: Meta-Learning Signed Distance Functions

CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances

Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation

Deep Automodulators

Autoregressive Score Matching

Compositional Visual Generation with Energy Based Models

How does This Interaction Affect Me? Interpretable Attribution for Feature Interactions

Domain Adaptation as a Problem of Inference on Graphical Models

Fast Unbalanced Optimal Transport on a Tree

Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators

O(n) Connections are Expressive Enough: Universal Approximability of Sparse Transformers

A Universal Approximation Theorem of Deep Neural Networks for Expressing Probability Distributions

Robust Sub-Gaussian Principal Component Analysis and Width-Independent Schatten Packing

Is Plug-in Solver Sample-Efficient for Feature-based Reinforcement Learning?

Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Framework

Preference learning along multiple criteria: A game-theoretic perspective

On Correctness of Automatic Differentiation for Non-Differentiable Functions

Robust Gaussian Covariance Estimation in Nearly-Matrix Multiplication Time

Cooperative Multi-player Bandit Optimization

Neutralizing Self-Selection Bias in Sampling for Sortition

The Complete Lasso Tradeoff Diagram

Quantifying the Empirical Wasserstein Distance to a Set of Measures: Beating the Curse of Dimensionality

Distributional Robustness with IPMs and links to Regularization and GANs

Towards Convergence Rate Analysis of Random Forests for Classification

Learning to Mutate with Hypergradient Guided Population

Robust Disentanglement of a Few Factors at a Time using rPU-VAE

Self-Supervised Graph Transformer on Large-Scale Molecular Data

TorsionNet: A Reinforcement Learning Approach to Sequential Conformer Search

CogMol: Target-Specific and Selective Drug Design for COVID-19 Using Deep Generative Models

TaylorGAN: Neighbor-Augmented Policy Update Towards Sample-Efficient Natural Language Generation

Towards Interpretable Natural Language Understanding with Explanations as Latent Variables

Learning to summarize with human feedback

Language-Conditioned Imitation Learning for Robot Manipulation Tasks

Guiding Deep Molecular Optimization with Genetic Exploration

What is being transferred in transfer learning?

What shapes feature representations? Exploring datasets, architectures, and training

FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training

Benchmarking Deep Learning Interpretability in Time Series Predictions

Stochastic Deep Gaussian Processes over Graphs

Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks

Rethinking Learnable Tree Filter for Generic Feature Transform

SOLOv2: Dynamic and Fast Instance Segmentation

HOI Analysis: Integrating and Decomposing Human-Object Interaction

RANet: Region Attention Network for Semantic Segmentation

ICNet: Intra-saliency Correlation Network for Co-Saliency Detection

Few-Cost Salient Object Detection with Adversarial-Paced Learning

Detecting Hands and Recognizing Physical Contact in the Wild

Targeted Adversarial Perturbations for Monocular Depth Prediction

Self-Supervised Visual Representation Learning from Hierarchical Grouping

Learning Affordance Landscapes for Interaction Exploration in 3D Environments

Deep Variational Instance Segmentation

Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation

Fine-Grained Dynamic Head for Object Detection

Learning About Objects by Learning to Interact with Them

Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D

Optimal visual search based on a model of target detectability in natural images

Online Influence Maximization under Linear Threshold Model

Profile Entropy: A Fundamental Measure for the Learnability and Compressibility of Distributions

(ends 11:00 PM)

WED 9 DEC

1 a.m.

Tutorial:

(Track1) Advances in Approximate Inference Q&A

(ends 1:50 AM)

1:40 a.m.

Affinity Workshop:

Women in Machine Learning

(ends 6:00 PM)

3 a.m.

Tutorial:

(Track2) Explaining Machine Learning Predictions: State-of-the-art, Challenges, and Opportunities Q&A

(ends 3:50 AM)

5 a.m.

Invited Talk (Posner Lecture):

The Real AI Revolution

Chris Bishop

(ends 7:00 AM)

6 a.m.

Demonstrations 1 [6:00-9:20]

Tue demos repeat on Wed

Demonstration s 6:00-9:20

MONICA: MObile Neural voIce Command Assistant for mobile games

tspDB: Time Series Predict DB

Probing Embedding Spaces in Deep Neural Networks

IBM Federated Learning Community Edition: An Interactive Demonstration

MolDesigner: Interactive Design of Efficacious Drugs with Deep Learning

MosAIc: Finding Artistic Connections across Culture with Conditional Image Retrieval

RetaiL: Open your own grocery store to reduce waste

PrototypeML: Visual Design of Arbitrarily Complex Neural Networks

A Knowledge Graph Reasoning Prototype

Shared Interest: Human Annotations vs. AI Saliency

(duration 3.3 hr)

Orals & Spotlights Track 15: COVID/Applications/Composition [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] High-Fidelity Generative Image Compression

[6:15] Learning Composable Energy Surrogates for PDE Order Reduction

[6:30] Hierarchically Organized Latent Modules for Exploratory Search in Morphogenetic Systems

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] Compositional Generalization by Learning Analytical Expressions

[7:10] Modern Hopfield Networks and Attention for Immune Repertoire Classification

[7:20] ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on Nonlinear ICA

[7:30] A causal view of compositional zero-shot recognition

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:40

[7:50] RetroXpert: Decompose Retrosynthesis Prediction Like A Chemist

[8:00] Barking up the right tree: an approach to search over molecule synthesis DAGs

[8:10] Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views

[8:20] Experimental design for MRI by greedy policy search

[8:30] How Robust are the Estimated Effects of Nonpharmaceutical Interventions against COVID-19?

Q&A s 8:40-8:50

[8:40] Joint Q&A for Preceeding Spotlights

Break s 8:50-9:00

Break

(ends 9:00 AM)

Orals & Spotlights Track 16: Continual/Meta/Misc Learning [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Continual Deep Learning by Functional Regularisation of Memorable Past

[6:15] Look-ahead Meta Learning for Continual Learning

[6:30] NeuMiss networks: differentiable programming for supervised learning with missing values.

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] Meta-trained agents implement Bayes-optimal agents

[7:10] Linear Dynamical Systems as a Core Computational Primitive

[7:20] Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels

[7:30] Uncertainty-aware Self-training for Few-shot Text Classification

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:40

[7:50] HiPPO: Recurrent Memory with Optimal Polynomial Projections

[8:00] Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity

[8:10] Leap-Of-Thought: Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge

[8:20] Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning

[8:30] Instead of Rewriting Foreign Code for Machine Learning, Automatically Synthesize Fast Gradients

Q&A s 8:40-8:50

[8:40] Joint Q&A for Preceeding Spotlights

Break s 8:50-9:00

Break

(ends 9:00 AM)

Orals & Spotlights Track 17: Kernel Methods/Optimization [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Learning with Operator-valued Kernels in Reproducing Kernel Krein Spaces

[6:15] Kernel Methods Through the Roof: Handling Billions of Points Efficiently

[6:30] A Group-Theoretic Framework for Data Augmentation

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] A mathematical model for automatic differentiation in machine learning

[7:10] A kernel test for quasi-independence

[7:20] Fourier Sparse Leverage Scores and Approximate Kernel Learning

[7:30] BOSS: Bayesian Optimization over String Spaces

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:30

[7:50] Fast geometric learning with symbolic matrices

[8:00] Training Stronger Baselines for Learning to Optimize

[8:10] Learning Linear Programs from Optimal Decisions

[8:20] Automatically Learning Compact Quality-aware Surrogates for Optimization Problems

Q&A s 8:30-8:40

[8:30] Joint Q&A for Preceeding Spotlights

Break s 8:40-9:00

Break

(ends 9:00 AM)

Orals & Spotlights Track 18: Deep Learning [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Ultra-Low Precision 4-bit Training of Deep Neural Networks

[6:15] Reservoir Computing meets Recurrent Kernels and Structured Transforms

[6:30] The interplay between randomness and structure during learning in RNNs

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] What if Neural Networks had SVDs?

[7:10] Practical Quasi-Newton Methods for Training Deep Neural Networks

[7:20] Triple descent and the two kinds of overfitting: where & why do they appear?

[7:30] On the linearity of large non-linear models: when and why the tangent kernel is constant

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:20

[7:50] Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy

[8:00] Proximal Mapping for Deep Regularization

[8:10] BoxE: A Box Embedding Model for Knowledge Base Completion

Q&A s 8:20-8:30

[8:20] Joint Q&A for Preceeding Spotlights

Break s 8:30-9:00

Break

(ends 9:00 AM)

Orals & Spotlights Track 19: Probabilistic/Causality [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Network-to-Network Translation with Conditional Invertible Neural Networks

[6:15] Causal Imitation Learning With Unobserved Confounders

[6:30] Gradient Estimation with Stochastic Softmax Tricks

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] Generalized Independent Noise Condition for Estimating Latent Variable Causal Graphs

[7:10] A Randomized Algorithm to Reduce the Support of Discrete Measures

[7:20] A/B Testing in Dense Large-Scale Networks: Design and Inference

[7:30] DisARM: An Antithetic Gradient Estimator for Binary Latent Variables

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:40

[7:50] Off-Policy Evaluation and Learning for External Validity under a Covariate Shift

[8:00] Sense and Sensitivity Analysis: Simple Post-Hoc Analysis of Bias Due to Unobserved Confounding

[8:10] Differentiable Causal Discovery from Interventional Data

[8:20] Bayesian Causal Structural Learning with Zero-Inflated Poisson Bayesian Networks

[8:30] Efficient semidefinite-programming-based inference for binary and multi-class MRFs

Q&A s 8:40-8:50

[8:40] Joint Q&A for Preceeding Spotlights

Break s 8:50-9:00

Break

(ends 9:00 AM)

Orals & Spotlights Track 20: Social/Adversarial Learning [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles

[6:15] Metric-Free Individual Fairness in Online Learning

[6:30] Fair regression via plug-in estimator and recalibration with statistical guarantees

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] Explaining Naive Bayes and Other Linear Classifiers with Polynomial Time and Delay

[7:10] Differentially-Private Federated Linear Bandits

[7:20] Adversarial Training is a Form of Data-dependent Operator Norm Regularization

[7:30] Prediction with Corrupted Expert Advice

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:40

[7:50] Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defenses

[8:00] Towards Safe Policy Improvement for Non-Stationary MDPs

[8:10] Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations

[8:20] Algorithmic recourse under imperfect causal knowledge: a probabilistic approach

[8:30] Understanding Gradient Clipping in Private SGD: A Geometric Perspective

Q&A s 8:40-8:50

[8:40] Joint Q&A for Preceeding Spotlights

Break s 8:50-9:00

Break

(ends 9:00 AM)

Orals & Spotlights Track 21: Optimization [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-7:00

[6:00] Hogwild!: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent

[6:15] Entropic Optimal Transport between Unbalanced Gaussian Measures has a Closed Form

[6:30] Acceleration with a Ball Optimization Oracle

[6:45] Convex optimization based on global lower second-order models

Spotlight s 7:00-7:40

[7:00] Adam with Bandit Sampling for Deep Learning

[7:10] Explore Aggressively, Update Conservatively: Stochastic Extragradient Methods with Variable Stepsize Scaling

[7:20] IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method

[7:30] Revisiting Frank-Wolfe for Polytopes: Strict Complementarity and Sparsity

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:40

[7:50] Minibatch Stochastic Approximate Proximal Point Methods

[8:00] Finding Second-Order Stationary Points Efficiently in Smooth Nonconvex Linearly Constrained Optimization Problems

[8:10] Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms

[8:20] Linearly Converging Error Compensated SGD

[8:30] Learning Augmented Energy Minimization via Speed Scaling

Q&A s 8:40-8:50

[8:40] Joint Q&A for Preceeding Spotlights

Break s 8:50-9:00

Break

(ends 9:00 AM)

9 a.m.

Poster Session 4 [9:00-11:00]

Model Fusion via Optimal Transport

What if Neural Networks had SVDs?

Understanding and Improving Fast Adversarial Training

Posterior Re-calibration for Imbalanced Datasets

Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout

GCN meets GPU: Decoupling “When to Sample” from “How to Sample”

Improving model calibration with accuracy versus uncertainty optimization

Deep Evidential Regression

Practical Quasi-Newton Methods for Training Deep Neural Networks

Ultra-Low Precision 4-bit Training of Deep Neural Networks

Improving Neural Network Training in Low Dimensional Random Bases

Bandit Samplers for Training Graph Neural Networks

ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training

Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation

Bayesian filtering unifies adaptive and non-adaptive neural network optimization methods

MomentumRNN: Integrating Momentum into Recurrent Neural Networks

Why are Adaptive Methods Good for Attention Models?

MESA: Boost Ensemble Imbalanced Learning with MEta-SAmpler

Dark Experience for General Continual Learning: a Strong, Simple Baseline

RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning

Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks

Continual Deep Learning by Functional Regularisation of Memorable Past

Look-ahead Meta Learning for Continual Learning

A Combinatorial Perspective on Transfer Learning

Continual Learning in Low-rank Orthogonal Subspaces

Mitigating Forgetting in Online Continual Learning via Instance-Aware Parameterization

Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning

Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels

Task-Robust Model-Agnostic Meta-Learning

Learning to Learn Variational Semantic Memory

Continuous Meta-Learning without Tasks

Auxiliary Task Reweighting for Minimum-data Learning

Hierarchically Organized Latent Modules for Exploratory Search in Morphogenetic Systems

Estimation and Imputation in Probabilistic Principal Component Analysis with Missing Not At Random Data

PLANS: Neuro-Symbolic Program Learning from Videos

Probabilistic Linear Solvers for Machine Learning

A/B Testing in Dense Large-Scale Networks: Design and Inference

Dual Instrumental Variable Regression

Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks

Gradient Regularized V-Learning for Dynamic Treatment Regimes

Identifying Causal-Effect Inference Failure with Uncertainty-Aware Models

Causal Estimation with Functional Confounders

Counterfactual Prediction for Bundle Treatment

Minimax Estimation of Conditional Moment Models

Off-Policy Evaluation and Learning for External Validity under a Covariate Shift

Sense and Sensitivity Analysis: Simple Post-Hoc Analysis of Bias Due to Unobserved Confounding

Multi-task Causal Learning with Gaussian Processes

Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models

Algorithmic recourse under imperfect causal knowledge: a probabilistic approach

Compositional Generalization via Neural-Symbolic Stack Machines

Learning Invariants through Soft Unification

Linear Disentangled Representations and Unsupervised Action Estimation

Identifying Mislabeled Data using the Area Under the Margin Ranking

A Bayesian Nonparametrics View into Deep Representations

Learning Invariances in Neural Networks from Training Data

Inverse Learning of Symmetries

Post-training Iterative Hierarchical Data Augmentation for Deep Networks

Exemplar VAE: Linking Generative Models, Nearest Neighbor Retrieval, and Data Augmentation

Goal-directed Generation of Discrete Structures with Conditional Generative Models

CoSE: Compositional Stroke Embeddings

A Causal View on Robustness of Neural Networks

Regularizing Towards Permutation Invariance In Recurrent Models

STLnet: Signal Temporal Logic Enforced Multivariate Recurrent Neural Networks

Generative causal explanations of black-box classifiers

Assessing SATNet's Ability to Solve the Symbol Grounding Problem

Towards Better Generalization of Adaptive Gradient Methods

Adam with Bandit Sampling for Deep Learning

Random Reshuffling: Simple Analysis with Vast Improvements

Explore Aggressively, Update Conservatively: Stochastic Extragradient Methods with Variable Stepsize Scaling

Boosting First-Order Methods by Shifting Objective: New Schemes with Faster Worst-Case Rates

A Catalyst Framework for Minimax Optimization

Global Convergence and Variance Reduction for a Class of Nonconvex-Nonconcave Minimax Problems

On the Almost Sure Convergence of Stochastic Gradient Descent in Non-Convex Problems

Hybrid Variance-Reduced SGD Algorithms For Minimax Problems with Nonconvex-Linear Function

An Improved Analysis of Stochastic Gradient Descent with Momentum

Robustness Analysis of Non-Convex Stochastic Gradient Descent using Biased Expectations

Online Robust Regression via SGD on the l1 loss

Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping

Large-Scale Methods for Distributionally Robust Optimization

Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms

Stochastic Recursive Gradient Descent Ascent for Stochastic Nonconvex-Strongly-Concave Minimax Problems

Provable Overlapping Community Detection in Weighted Graphs

Improving Inference for Neural Image Compression

Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning

Kernel Methods Through the Roof: Handling Billions of Points Efficiently

Discovering conflicting groups in signed networks

StratLearner: Learning a Strategy for Misinformation Prevention in Social Networks

Learning Differentiable Programs with Admissible Neural Heuristics

Neural Execution Engines: Learning to Execute Subroutines

Multimodal Graph Networks for Compositional Generalization in Visual Question Answering

RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning

SEVIR : A Storm Event Imagery Dataset for Deep Learning Applications in Radar and Satellite Meteorology

Instead of Rewriting Foreign Code for Machine Learning, Automatically Synthesize Fast Gradients

Fast geometric learning with symbolic matrices

Synbols: Probing Learning Algorithms with Synthetic Datasets

Evaluating Attribution for Graph Neural Networks

Accelerating Reinforcement Learning through GPU Atari Emulation

Adaptive Gradient Quantization for Data-Parallel SGD

Universally Quantized Neural Compression

Searching for Low-Bit Weights in Quantized Neural Networks

Bayesian Bits: Unifying Quantization and Pruning

FleXOR: Trainable Fractional Quantization

Robust Quantization: One Model to Rule Them All

A Statistical Framework for Low-bitwidth Training of Deep Neural Networks

Invertible Gaussian Reparameterization: Revisiting the Gumbel-Softmax

DisARM: An Antithetic Gradient Estimator for Binary Latent Variables

Efficient semidefinite-programming-based inference for binary and multi-class MRFs

Gradient Estimation with Stochastic Softmax Tricks

Quantized Variational Inference

Approximation Based Variance Reduction for Reparameterization Gradients

VarGrad: A Low-Variance Gradient Estimator for Variational Inference

Optimal Variance Control of the Score-Function Gradient Estimator for Importance-Weighted Bounds

AutoPrivacy: Automated Layer-wise Parameter Selection for Secure Neural Network Inference

Group-Fair Online Allocation in Continuous Time

Fair Hierarchical Clustering

Approximate Heavily-Constrained Learning with Lagrange Multiplier Models

Metric-Free Individual Fairness in Online Learning

Fair regression via plug-in estimator and recalibration with statistical guarantees

Fair Multiple Decision Making Through Soft Interventions

Intra-Processing Methods for Debiasing Neural Networks

Ensuring Fairness Beyond the Training Data

Fair Performance Metric Elicitation

Fairness without Demographics through Adversarially Reweighted Learning

Exploiting MMD and Sinkhorn Divergences for Fair and Transferable Representation Learning

How do fair decisions fare in long-term qualification?

Fair regression with Wasserstein barycenters

Learning Certified Individually Fair Representations

Fairness with Overlapping Groups; a Probabilistic Perspective

Consistent Plug-in Classifiers for Complex Objectives and Constraints

Causal Discovery in Physical Systems from Videos

Causal Imitation Learning With Unobserved Confounders

A Class of Algorithms for General Instrumental Variable Models

Active Invariant Causal Prediction: Experiment Selection through Stability

Causal Discovery from Soft Interventions with Unknown Targets: Characterization and Learning

Deep Structural Causal Models for Tractable Counterfactual Inference

Reconsidering Generative Objectives For Counterfactual Reasoning

High-recall causal discovery for autocorrelated time series with latent confounders

Applications of Common Entropy for Causal Inference

Entropic Causal Inference: Identifiability and Finite Sample Results

General Transportability of Soft Interventions: Completeness Results

Learning Causal Effects via Weighted Empirical Risk Minimization

Differentiable Causal Discovery from Interventional Data

Generalized Independent Noise Condition for Estimating Latent Variable Causal Graphs

Bayesian Causal Structural Learning with Zero-Inflated Poisson Bayesian Networks

A polynomial-time algorithm for learning nonparametric causal graphs

Linear Time Sinkhorn Divergences using Positive Features

Learning Kernel Tests Without Data Splitting

Learning with Operator-valued Kernels in Reproducing Kernel Krein Spaces

A kernel test for quasi-independence

Hard Shape-Constrained Kernel Machines

Statistical Optimal Transport posed as Learning Kernel Embedding

Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search

Continuous Regularized Wasserstein Barycenters

Entropic Optimal Transport between Unbalanced Gaussian Measures has a Closed Form

Multi-Fidelity Bayesian Optimization via Deep Neural Networks

Re-Examining Linear Embeddings for High-Dimensional Bayesian Optimization

Hybrid Models for Learning to Branch

Interior Point Solving for LP-based prediction+optimisation

Curriculum learning for multilevel budgeted combinatorial problems

BOSS: Bayesian Optimization over String Spaces

An implicit function learning approach for parametric modal regression

Adversarial Example Games

Robust Pre-Training by Adversarial Contrastive Learning

Provably Robust Metric Learning

A Game Theoretic Analysis of Additive Adversarial Attacks and Defenses

Adversarial Training is a Form of Data-dependent Operator Norm Regularization

Adversarial Robustness of Supervised Sparse Coding

Boosting Adversarial Training with Hypersphere Embedding

On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them

DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles

Attack of the Tails: Yes, You Really Can Backdoor Federated Learning

Adversarially Robust Few-Shot Learning: A Meta-Learning Approach

Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defenses

Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferability

Robustness of Bayesian Neural Networks to Gradient-Based Attacks

Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations

On Adaptive Attacks to Adversarial Example Defenses

High-Fidelity Generative Image Compression

Attribute Prototype Network for Zero-Shot Learning

Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies

Variational Interaction Information Maximization for Cross-domain Disentanglement

Hard Example Generation by Texture Synthesis for Cross-domain Shape Similarity Learning

Few-shot Image Generation with Elastic Weight Consolidation

DeepI2I: Enabling Deep Hierarchical Image-to-Image Translation by Transferring from GANs

Generating Correct Answers for Progressive Matrices Intelligence Tests

GramGAN: Deep 3D Texture Synthesis From 2D Exemplars

Network-to-Network Translation with Conditional Invertible Neural Networks

Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation

Instance Selection for GANs

Quantifying Learnability and Describability of Visual Concepts Emerging in Representation Learning

ICAM: Interpretable Classification via Disentangled Representations and Feature Attribution Mapping

Smoothed Geometry for Robust Attribution

Neural Networks with Recurrent Generative Feedback

COT-GAN: Generating Sequential Data via Causal Optimal Transport

ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on Nonlinear ICA

Unsupervised Learning of Lagrangian Dynamics from Images for Prediction and Control

Implicit Rank-Minimizing Autoencoder

Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Class-Imbalanced Data

Set2Graph: Learning Graphs From Sets

Efficient Generation of Structured Objects with Constrained Adversarial Networks

Improving GAN Training with Probability Ratio Clipping and Sample Reweighting

Regularized linear autoencoders recover the principal components, eventually

BoxE: A Box Embedding Model for Knowledge Base Completion

BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images

Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views

Deep Statistical Solvers

Learning of Discrete Graphical Models with Neural Networks

Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity

Falcon: Fast Spectral Inference on Encrypted Data

Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers

Learning Composable Energy Surrogates for PDE Order Reduction

AvE: Assistance via Empowerment

EcoLight: Intersection Control in Developing Regions Under Extreme Budget and Network Constraints

RetroXpert: Decompose Retrosynthesis Prediction Like A Chemist

Barking up the right tree: an approach to search over molecule synthesis DAGs

Synthesizing Tasks for Block-based Programming

Deep Imitation Learning for Bimanual Robotic Manipulation

PRANK: motion Prediction based on RANKing

Meta-trained agents implement Bayes-optimal agents

On the equivalence of molecular graph convolution and molecular wave function with poor basis set

Dynamic allocation of limited memory resources in reinforcement learning

Ensembling geophysical models with Bayesian Neural Networks

Neurosymbolic Transformers for Multi-Agent Communication

Avoiding Side Effects By Considering Future Tasks

What Did You Think Would Happen? Explaining Agent Behaviour through Intended Outcomes

Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals

Learning Mutational Semantics

Zero-Resource Knowledge-Grounded Dialogue Generation

Representation Learning for Integrating Multi-domain Outcomes to Optimize Individualized Treatment

Causal analysis of Covid-19 Spread in Germany

Dynamic Fusion of Eye Movement Data and Verbal Narrations in Knowledge-rich Domains

X-CAL: Explicit Calibration for Survival Analysis

Experimental design for MRI by greedy policy search

How Robust are the Estimated Effects of Nonpharmaceutical Interventions against COVID-19?

OrganITE: Optimal transplant donor organ offering using an individual treatment effect

When Counterpoint Meets Chinese Folk Melodies

BERT Loses Patience: Fast and Robust Inference with Early Exit

Unsupervised Text Generation by Learning from Search

Leap-Of-Thought: Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge

A Spectral Energy Distance for Parallel Speech Synthesis

Compositional Generalization by Learning Analytical Expressions

A Measure-Theoretic Approach to Kernel Conditional Mean Embeddings

Kernel Alignment Risk Estimator: Risk Prediction from Training Data

Fourier Sparse Leverage Scores and Approximate Kernel Learning

Demystifying Orthogonal Monte Carlo and Beyond

Unfolding recurrence by Green’s functions for optimized reservoir computing

A Group-Theoretic Framework for Data Augmentation

Understanding Double Descent Requires A Fine-Grained Bias-Variance Decomposition

Triple descent and the two kinds of overfitting: where & why do they appear?

The interplay between randomness and structure during learning in RNNs

A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent

When Do Neural Networks Outperform Kernel Methods?

The Statistical Cost of Robust Kernel Hyperparameter Turning

Asymptotic normality and confidence intervals for derivatives of 2-layers neural network in the random features model

Randomized tests for high-dimensional regression: A more efficient and powerful solution

Sample complexity and effective dimension for regression on manifolds

An analytic theory of shallow networks dynamics for hinge loss classification

Mix and Match: An Optimistic Tree-Search Approach for Learning Models from Mixture Distributions

One-bit Supervision for Image Classification

Your Classifier can Secretly Suffice Multi-Source Domain Adaptation

Early-Learning Regularization Prevents Memorization of Noisy Labels

Compositional Zero-Shot Learning via Fine-Grained Dense Feature Composition

Universal Domain Adaptation through Self Supervision

Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift

A causal view of compositional zero-shot recognition

CompRess: Self-Supervised Learning by Compressing Representations

Big Self-Supervised Models are Strong Semi-Supervised Learners

Provably Consistent Partial-Label Learning

Multifaceted Uncertainty Estimation for Label-Efficient Deep Learning

Unsupervised Translation of Programming Languages

Uncertainty-aware Self-training for Few-shot Text Classification

Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching

Teaching a GAN What Not to Learn

A Randomized Algorithm to Reduce the Support of Discrete Measures

Statistical Efficiency of Thompson Sampling for Combinatorial Semi-Bandits

Follow the Perturbed Leader: Optimism and Fast Parallel Algorithms for Smooth Minimax Games

Better Full-Matrix Regret via Parameter-Free Online Learning

Locally-Adaptive Nonparametric Online Learning

Online Learning with Primary and Secondary Losses

Online Linear Optimization with Many Hints

Exploiting the Surrogate Gap in Online Multiclass Classification

Temporal Variability in Implicit Online Learning

Prediction with Corrupted Expert Advice

A mathematical model for automatic differentiation in machine learning

Online Non-Convex Optimization with Imperfect Feedback

Adaptive Importance Sampling for Finite-Sum Optimization and Sampling with Decreasing Step-Sizes

Differentially-Private Federated Linear Bandits

Learning Strategy-Aware Linear Classifiers

BRP-NAS: Prediction-based NAS using GCNs

Neural Architecture Generator Optimization

Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS

AutoSync: Learning to Synchronize for Data-Parallel Distributed Deep Learning

Agnostic Learning with Multiple Objectives

Training Stronger Baselines for Learning to Optimize

GPU-Accelerated Primal Learning for Extremely Fast Large-Scale Classification

Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge

Geometric Dataset Distances via Optimal Transport

Efficient Algorithms for Device Placement of DNN Graph Operators

Automatically Learning Compact Quality-aware Surrogates for Optimization Problems

Bayesian Optimization for Iterative Learning

Model Selection for Production System via Automated Online Experiments

Interpretable and Personalized Apprenticeship Scheduling: Learning Interpretable Scheduling Policies from Heterogeneous User Demonstrations

CryptoNAS: Private Inference on a ReLU Budget

Neural Power Units

Diversity-Guided Multi-Objective Bayesian Optimization With Batch Evaluations

High-Dimensional Bayesian Optimization via Nested Riemannian Manifolds

Learning Feature Sparse Principal Subspace

Fast Epigraphical Projection-based Incremental Algorithms for Wasserstein Distributionally Robust Support Vector Machine

Stochastic Optimization with Laggard Data Pipelines

Black-Box Optimization with Local Generative Surrogates

Learning Linear Programs from Optimal Decisions

Acceleration with a Ball Optimization Oracle

Convex optimization based on global lower second-order models

Walking in the Shadow: A New Perspective on Descent Directions for Constrained Minimization

Revisiting Frank-Wolfe for Polytopes: Strict Complementarity and Sparsity

Sub-linear Regret Bounds for Bayesian Optimisation in Unknown Search Spaces

An efficient nonconvex reformulation of stagewise convex optimization problems

Finding Second-Order Stationary Points Efficiently in Smooth Nonconvex Linearly Constrained Optimization Problems

BoTorch: A Framework for Efficient Monte-Carlo Bayesian Optimization

First-Order Methods for Large-Scale Market Equilibrium Computation

Trade-offs and Guarantees of Adversarial Representation Learning for Information Obfuscation

Explaining Naive Bayes and Other Linear Classifiers with Polynomial Time and Delay

Deep Smoothing of the Implied Volatility Surface

What went wrong and when? Instance-wise feature importance for time-series black-box models

Learning from Failure: De-biasing Classifier from Biased Classifier

Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability

Learning Global Transparent Models consistent with Local Contrastive Explanations

Towards Safe Policy Improvement for Non-Stationary MDPs

Decisions, Counterfactual Explanations and Strategic Behavior

From Predictions to Decisions: Using Lookahead Regularization

Model Agnostic Multilevel Explanations

Achieving Equalized Odds by Resampling Sensitive Attributes

Regularizing Black-box Models for Improved Interpretability

Glyph: Fast and Accurately Training Deep Neural Networks on Encrypted Data

MetaPoison: Practical General-purpose Clean-label Data Poisoning

Understanding Gradient Clipping in Private SGD: A Geometric Perspective

Coresets via Bilevel Optimization for Continual Learning and Streaming

Linear Dynamical Systems as a Core Computational Primitive

BanditPAM: Almost Linear Time k-Medoids Clustering via Multi-Armed Bandits

Sliding Window Algorithms for k-Clustering Problems

Fast and Accurate

$k$ -means++ via Rejection Sampling

NeuMiss networks: differentiable programming for supervised learning with missing values.

Debiasing Averaged Stochastic Gradient Descent to handle missing values

Coresets for Near-Convex Functions

HiPPO: Recurrent Memory with Optimal Polynomial Projections

Online MAP Inference of Determinantal Point Processes

Joints in Random Forests

Approximate Cross-Validation for Structured Models

A convex optimization formulation for multivariate regression

Adaptive Reduced Rank Regression

Self-Distillation Amplifies Regularization in Hilbert Space

Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? --- A Neural Tangent Kernel Perspective

Neural Path Features and Neural Path Kernel : Understanding the role of gates in deep learning

Explicit Regularisation in Gaussian Noise Injections

Rational neural networks

On the Similarity between the Laplace and Neural Tangent Kernels

Neural Anisotropy Directions

Ode to an ODE

Label-Aware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity

Limits to Depth Efficiencies of Self-Attention

On the linearity of large non-linear models: when and why the tangent kernel is constant

Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy

Directional Pruning of Deep Neural Networks

Winning the Lottery with Continuous Sparsification

Analytic Characterization of the Hessian in Shallow ReLU Models: A Tale of Symmetry

On the universality of deep learning

Reservoir Computing meets Recurrent Kernels and Structured Transforms

The Diversified Ensemble Neural Network

AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning

Spin-Weighted Spherical CNNs

Autoencoders that don't overfit towards the Identity

Modern Hopfield Networks and Attention for Immune Repertoire Classification

UCSG-NET- Unsupervised Discovering of Constructive Solid Geometry Tree

UCLID-Net: Single View Reconstruction in Object Space

Graph Geometry Interaction Learning

Feature Importance Ranking for Deep Learning

Introducing Routing Uncertainty in Capsule Networks

The Pitfalls of Simplicity Bias in Neural Networks

Primal-Dual Mesh Convolutional Neural Networks

The Convolution Exponential and Generalized Sylvester Flows

Coherent Hierarchical Multi-Label Classification Networks

Differentiable Top-k with Optimal Transport

Proximal Mapping for Deep Regularization

CSER: Communication-efficient SGD with Error Reset

Practical Low-Rank Communication Compression in Decentralized Deep Learning

A Decentralized Parallel Algorithm for Training Generative Adversarial Nets

Second Order Optimality in Decentralized Non-Convex Optimization via Perturbed Gradient Tracking

Distributed Newton Can Communicate Less and Resist Byzantine Workers

IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method

Dual-Free Stochastic Decentralized Optimization with Variance Reduction

FedSplit: an algorithmic framework for fast federated optimization

Distributionally Robust Federated Averaging

Personalized Federated Learning with Moreau Envelopes

Minibatch vs Local SGD for Heterogeneous Distributed Learning

Minibatch Stochastic Approximate Proximal Point Methods

Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach

A Simple and Efficient Smoothing Method for Faster Optimization and Local Exploration

Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms

Linearly Converging Error Compensated SGD

The All-or-Nothing Phenomenon in Sparse Tensor PCA

Closing the Dequantization Gap: PixelCNN as a Single-Layer Flow

ImpatientCapsAndRuns: Approximately Optimal Algorithm Configuration from an Infinite Pool

Normalizing Kalman Filters for Multivariate Time Series Analysis

Learning Augmented Energy Minimization via Speed Scaling

(ends 11:00 AM)

11 a.m.

Memorial:

In Memory of Olivier Chapelle

(ends 12:00 PM)

noon

Symposium:

COVID-19 Symposium Day 2

(ends 4:00 PM)

Tutorial:

(Track2) Practical Uncertainty Estimation and Out-of-Distribution Robustness in Deep Learning Q&A

(ends 12:50 PM)

2 p.m.

Tutorial:

(Track1) Abstraction & Reasoning in AI systems: Modern Perspectives Q&A

(ends 2:50 PM)

5 p.m.

Invited Talk:

A Future of Work for the Invisible Workers in A.I.

Saiph Savage

(ends 7:00 PM)

6 p.m.

Demonstrations 2 [6:00-9:20]

Tue demos repeat on Wed

Demonstration s 6:00-9:20

LMdiff: A Visual Diff Tool to Compare LanguageModels

AI Assisted Data Labeling

Automated dataset extraction from SEC filings

Generating Novelty in Open-World Multi-Agent Strategic Board Games

Fast and Automatic Visual Label Conflict Resolution

DeepRacing AI - Autonomous Motorsport Racing

ColliFlow: A Library for Executing Collaborative Intelligence Graphs

Musical Speech: A Transformer-based Composition Tool

xLP: Explainable Link Prediction Demo

Coreference Resolution for Neutralizing Gendered Pronouns

(duration 3.3 hr)

Orals & Spotlights Track 22: Vision Applications [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Learning Implicit Functions for Topology-Varying Dense 3D Shape Correspondence

[6:15] LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration

[6:30] The Origins and Prevalence of Texture Bias in Convolutional Neural Networks

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] Distribution Matching for Crowd Counting

[7:10] Texture Interpolation for Probing Visual Perception

[7:20] Consistent Structural Relation Learning for Zero-Shot Segmentation

[7:30] CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:30

[7:50] ShapeFlow: Learnable Deformation Flows Among 3D Shapes

[8:00] Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows

[8:10] Counterfactual Vision-and-Language Navigation: Unravelling the Unseen

[8:20] RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder

Q&A s 8:30-8:40

[8:30] Joint Q&A for Preceeding Spotlights

Break s 8:40-9:00

Break

(ends 9:00 PM)

Orals & Spotlights Track 23: Graph/Meta Learning/Software [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] FrugalML: How to use ML Prediction APIs more accurately and cheaply

[6:15] AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity

[6:30] PyGlove: Symbolic Programming for Automated Machine Learning

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] Improved Schemes for Episodic Memory-based Lifelong Learning

[7:10] Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting

[7:20] Uncertainty Aware Semi-Supervised Learning on Graph Data

[7:30] Rethinking Importance Weighting for Deep Learning under Distribution Shift

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:20

[7:50] Modular Meta-Learning with Shrinkage

[8:00] JAX MD: A Framework for Differentiable Physics

[8:10] RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference

Q&A s 8:20-8:30

[8:20] Joint Q&A for Preceeding Spotlights

Break s 8:30-9:00

Break

(ends 9:00 PM)

Orals & Spotlights Track 24: Learning Theory [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Improved guarantees and a multiple-descent curve for Column Subset Selection and the Nystrom method

[6:15] Bias no more: high-probability data-dependent regret bounds for adversarial bandits and MDPs

[6:30] Worst-Case Analysis for Randomly Collected Data

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] On Adaptive Distance Estimation

[7:10] Tight First- and Second-Order Regret Bounds for Adversarial Linear Bandits

[7:20] Delay and Cooperation in Nonstochastic Linear Bandits

[7:30] Unreasonable Effectiveness of Greedy Algorithms in Multi-Armed Bandit with Many Arms

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:40

[7:50] Simultaneously Learning Stochastic and Adversarial Episodic MDPs with Known Transition

[8:00] A Tight Lower Bound and Efficient Reduction for Swap Regret

[8:10] Estimation of Skill Distribution from a Tournament

[8:20] Optimal Prediction of the Number of Unseen Species with Multiplicity

[8:30] Estimating Rank-One Spikes from Heavy-Tailed Noise via Self-Avoiding Walks

Q&A s 8:40-8:50

[8:40] Joint Q&A for Preceeding Spotlights

Break s 8:50-9:00

Break

(ends 9:00 PM)

9 p.m.

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

Consistent Structural Relation Learning for Zero-Shot Segmentation

TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation

AOT: Appearance Optimal Transport Based Identity Swapping for Forgery Detection

UnModNet: Learning to Unwrap a Modulo Image for High Dynamic Range Imaging

Group Contextual Encoding for 3D Point Clouds

Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection

Dual-Resolution Correspondence Networks

Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation

Modeling Noisy Annotations for Crowd Counting

RSKDD-Net: Random Sample-based Keypoint Detector and Descriptor

Distribution Matching for Crowd Counting

Uncertainty-Aware Learning for Zero-Shot Semantic Segmentation

Every View Counts: Cross-View Consistency in 3D Object Detection with Hybrid-Cylindrical-Spherical Voxelization

RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder

Structured Convolutions for Efficient Neural Network Design

Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embedding

MuSCLE: Multi Sweep Compression of LiDAR using Deep Entropy Models

Ultrahyperbolic Representation Learning

Reparameterizing Mirror Descent as Gradient Descent

Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction

Handling Missing Data with Graph Representation Learning

Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completion

Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting

Timeseries Anomaly Detection using Temporal Hierarchical One-Class Network

How Can I Explain This to You? An Empirical Study of Deep Neural Network Explanation Methods

PEP: Parameter Ensembling by Perturbation

Wisdom of the Ensemble: Improving Consistency of Deep Learning Models

Unifying Activation- and Timing-based Learning Rules for Spiking Neural Networks

Dirichlet Graph Variational Autoencoder

Gradient Boosted Normalizing Flows

Improved Guarantees for k-means++ and k-means++ Parallel

Estimation of Skill Distribution from a Tournament

Transfer Learning via

$\ell_1$ Regularization

Robust Meta-learning for Mixed Linear Regression with Small Batches

Efficient Projection-free Algorithms for Saddle Point Problems

A Single-Loop Smoothed Gradient Descent-Ascent Algorithm for Nonconvex-Concave Min-Max Problems

A Fair Classifier Using Kernel Density Estimation

List-Decodable Mean Estimation via Iterative Multi-Filtering

On Learning Ising Models under Huber's Contamination Model

Worst-Case Analysis for Randomly Collected Data

Extrapolation Towards Imaginary 0-Nearest Neighbour and Its Improved Convergence Rate

A General Method for Robust Learning from Batches

Optimal Prediction of the Number of Unseen Species with Multiplicity

Probabilistic Active Meta-Learning

Meta-Consolidation for Continual Learning

Understanding the Role of Training Regimes in Continual Learning

Supermasks in Superposition

Improved Schemes for Episodic Memory-based Lifelong Learning

Continual Learning with Node-Importance based Adaptive Group Sparse Regularization

GAN Memory with No Forgetting

Meta-Learning with Adaptive Hyperparameters

Online Structured Meta-learning

Modeling and Optimization Trade-off in Meta-learning

Structured Prediction for Conditional Meta-Learning

Meta-learning from Tasks with Heterogeneous Attribute Spaces

Gradient-EM Bayesian Meta-Learning

MATE: Plugging in Model Awareness to Task Embedding for Meta Learning

Neural Complexity Measures

Modular Meta-Learning with Shrinkage

Gradient Surgery for Multi-Task Learning

Organizing recurrent network dynamics by task-computation to enable continual learning

Finding the Homology of Decision Boundaries with Active Learning

Exemplar Guided Active Learning

OOD-MAML: Meta-Learning for Few-Shot Out-of-Distribution Detection and Classification

An Unbiased Risk Estimator for Learning with Augmented Classes

Semi-Supervised Partial Label Learning via Confidence-Rated Margin Maximization

Rethinking Importance Weighting for Deep Learning under Distribution Shift

Robust Correction of Sampling Bias using Cumulative Distribution Functions

Learning from Positive and Unlabeled Data with Arbitrary Positive Shift

FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

A Variational Approach for Learning from Positive and Unlabeled Data

HRN: A Holistic Approach to One Class Learning

Rethinking the Value of Labels for Improving Class-Imbalanced Learning

wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations

Learning from Aggregate Observations

Self-training Avoids Using Spurious Features Under Domain Shift

Learning Physical Constraints with Neural Projections

Time-Reversal Symmetric ODE Network

AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity

Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networks

LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration

Adaptive Learning of Rank-One Models for Efficient Pairwise Sequence Alignment

Fourier-transform-based attribution priors improve the interpretability and stability of deep learning models for genomics

Counterfactual Vision-and-Language Navigation: Unravelling the Unseen

Neural FFTs for Universal Texture Image Synthesis

CodeCMR: Cross-Modal Retrieval For Function-Level Binary Source Code Matching

Synthesize, Execute and Debug: Learning to Repair for Neural Program Synthesis

EvolveGraph: Multi-Agent Trajectory Prediction with Dynamic Relational Reasoning

Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting

JAX MD: A Framework for Differentiable Physics

Multi-agent Trajectory Prediction with Fuzzy Query Attention

Learning Agent Representations for Ice Hockey

Correlation Robust Influence Maximization

On Adaptive Distance Estimation

Recovery of sparse linear classifiers from mixture of responses

Robustness of Community Detection to Random Geometric Perturbations

Entrywise convergence of iterative methods for eigenproblems

Optimal Iterative Sketching Methods with the Subsampled Randomized Hadamard Transform

Beyond Lazy Training for Over-parameterized Tensor Decomposition

Estimating Rank-One Spikes from Heavy-Tailed Noise via Self-Avoiding Walks

Improved guarantees and a multiple-descent curve for Column Subset Selection and the Nystrom method

Precise expressions for random projections: Low-rank approximation and randomized Newton

Matrix Completion with Hierarchical Graph Side Information

A Matrix Chernoff Bound for Markov Chains and Its Application to Co-occurrence Matrices

Fairness constraints can help exact inference in structured prediction

Exact expressions for double descent and implicit regularization via surrogate random design

SURF: A Simple, Universal, Robust, Fast Distribution Learning Algorithm

Uncertainty Aware Semi-Supervised Learning on Graph Data

Calibrated Reliable Regression using Maximum Mean Discrepancy

Energy-based Out-of-distribution Detection

Neural Manifold Ordinary Differential Equations

NanoFlow: Scalable Normalizing Flows with Sublinear Parameter Complexity

Adaptation Properties Allow Identification of Optimized Neural Codes

Reverse-engineering recurrent neural network solutions to a hierarchical inference task for mice

Learning to search efficiently for causally near-optimal treatments

General Control Functions for Causal Effect Estimation from IVs

Characterizing Optimal Mixed Policies: Where to Intervene and What to Observe

Active Structure Learning of Causal DAGs via Directed Clique Trees

Adaptive Experimental Design with Temporal Interference: A Maximum Likelihood Approach

Deep Relational Topic Modeling via Graph Poisson Gamma Belief Network

Promoting Stochasticity for Expressive Policies via a Simple and Efficient Regularization Method

Evaluating and Rewarding Teamwork Using Cooperative Game Abstractions

Efficient Distance Approximation for Structured High-Dimensional Distributions via Learning

Unreasonable Effectiveness of Greedy Algorithms in Multi-Armed Bandit with Many Arms

Batched Coarse Ranking in Multi-Armed Bandits

Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards

Bias no more: high-probability data-dependent regret bounds for adversarial bandits and MDPs

Stage-wise Conservative Linear Bandits

Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring

Tight First- and Second-Order Regret Bounds for Adversarial Linear Bandits

Delay and Cooperation in Nonstochastic Linear Bandits

An Empirical Process Approach to the Union Bound: Practical Algorithms for Combinatorial and Linear Bandits

Simultaneously Learning Stochastic and Adversarial Episodic MDPs with Known Transition

Dynamic Regret of Convex and Smooth Functions

Minimax Regret of Switching-Constrained Online Convex Optimization: No Phase Transition

Online learning with dynamics: A minimax perspective

A Tight Lower Bound and Efficient Reduction for Swap Regret

Making Non-Stochastic Control (Almost) as Easy as Stochastic

Non-Stochastic Control with Bandit Feedback

Learning Implicit Functions for Topology-Varying Dense 3D Shape Correspondence

Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernels

Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction

Generative 3D Part Assembly via Dynamic Graph Learning

Online Adaptation for Consistent Mesh Reconstruction in the Wild

Learning Deformable Tetrahedral Meshes for 3D Reconstruction

Weakly Supervised Deep Functional Maps for Shape Matching

Neural Star Domain as Primitive Representation

Robust Multi-Object Matching via Iterative Reweighting of the Graph Connection Laplacian

Grasp Proposal Networks: An End-to-End Solution for Visual Learning of Robotic Grasps

CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations

ShapeFlow: Learnable Deformation Flows Among 3D Shapes

Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows

The Origins and Prevalence of Texture Bias in Convolutional Neural Networks

Texture Interpolation for Probing Visual Perception

Byzantine Resilient Distributed Multi-Task Learning

FrugalML: How to use ML Prediction APIs more accurately and cheaply

Improving Auto-Augment via Augmentation-Wise Weight Sharing

ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding

RandAugment: Practical Automated Data Augmentation with a Reduced Search Space

Meta-Neighborhoods

A Closer Look at the Training Strategy for Modern Meta-Learning

Transferable Calibration with Lower Bias and Variance in Domain Adaptation

Unsupervised Learning of Object Landmarks via Self-Training Correspondence

Autofocused oracles for model-based design

Hierarchical Neural Architecture Search for Deep Stereo Matching

UWSOD: Toward Fully-Supervised-Level Capacity Weakly Supervised Object Detection

Hierarchical Granularity Transfer Learning

PyGlove: Symbolic Programming for Automated Machine Learning

Fast, Accurate, and Simple Models for Tabular Data via Augmented Distillation

RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference

TinyTL: Reduce Memory, Not Parameters for Efficient On-Device Learning

Distributed Distillation for On-Device Learning

(ends 11:00 PM)

THU 10 DEC

midnight

Tutorial:

(Track2) Deep Conversational AI Q&A

(ends 12:50 AM)

2 a.m.

Tutorial:

(Track3) Designing Learning Dynamics Q&A

(ends 2:50 AM)

3 a.m.

Tutorial:

(Track3) Deep Implicit Layers: Neural ODEs, Equilibrium Models, and Differentiable Optimization Q&A

(ends 3:50 AM)

4 a.m.

Town Hall:

NeurIPS Town Hall

(duration 1.0 hr)

5 a.m.

Invited Talk (Breiman Lecture):

Causal Learning

Marloes Maathuis

(ends 7:00 AM)

6 a.m.

Orals & Spotlights Track 25: Probabilistic Models/Statistics [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Training Normalizing Flows with the Information Bottleneck for Competitive Generative Classification

[6:15] Fast and Flexible Temporal Point Processes with Triangular Maps

[6:30] Greedy inference with structure-exploiting lazy maps

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] Sampling from a k-DPP without looking at all items

[7:10] Non-parametric Models for Non-negative Functions

[7:20] Distribution-free binary classification: prediction sets, confidence intervals and calibration

[7:30] Factor Graph Grammars

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:40

[7:50] Asymptotically Optimal Exact Minibatch Metropolis-Hastings

[8:00] Bayes Consistency vs. H-Consistency: The Interplay between Surrogate Loss Functions and the Scoring Function Class

[8:10] Confidence sequences for sampling without replacement

[8:20] Statistical and Topological Properties of Sliced Probability Divergences

[8:30] Testing Determinantal Point Processes

Q&A s 8:40-8:50

[8:40] Joint Q&A for Preceeding Spotlights

Break s 8:50-9:00

Break

(ends 9:00 AM)

Orals & Spotlights Track 26: Graph/Relational/Theory [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Graph Cross Networks with Vertex Infomax Pooling

[6:15] Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphs

[6:30] Graph Random Neural Networks for Semi-Supervised Learning on Graphs

Break s 6:45-7:00

Break

Spotlight s 7:00-7:20

[7:00] Learning Graph Structure With A Finite-State Automaton Layer

[7:10] Pointer Graph Networks

Q&A s 7:20-7:30

[7:20] Joint Q&A for Preceeding Spotlights

Spotlight s 7:30-7:40

[7:30] Certified Robustness of Graph Convolution Networks for Graph Classification under Topological Attacks

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:30

[7:50] Convergence and Stability of Graph Convolutional Networks on Large Random Graphs

[8:00] Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains

[8:10] Most ReLU Networks Suffer from

$\ell^2$ Adversarial Perturbations

[8:20] Beyond Perturbations: Learning Guarantees with Arbitrary Adversarial Test Examples

Q&A s 8:30-8:40

[8:30] Joint Q&A for Preceeding Spotlights

Break s 8:40-9:00

Break

(ends 9:00 AM)

Orals & Spotlights Track 27: Unsupervised/Probabilistic [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Contrastive learning of global and local features for medical image segmentation with limited annotations

[6:15] Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning

[6:30] SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] Self-Supervised Relational Reasoning for Representation Learning

[7:10] Object-Centric Learning with Slot Attention

[7:20] Telescoping Density-Ratio Estimation

[7:30] Probabilistic Inference with Algebraic Constraints: Theoretical Limits and Practical Approximations

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:30

[7:50] Path Sample-Analytic Gradient Estimators for Stochastic Binary Networks

[8:00] Stochastic Normalizing Flows

[8:10] Generative Neurosymbolic Machines

[8:20] DAGs with No Fears: A Closer Look at Continuous Optimization for Learning Bayesian Networks

Q&A s 8:30-8:40

[8:30] Joint Q&A for Preceeding Spotlights

Break s 8:40-9:00

Break

(ends 9:00 AM)

Orals & Spotlights Track 28: Deep Learning [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] A shooting formulation of deep learning

[6:15] On the training dynamics of deep networks with

$L_2$ regularization

[6:30] Compositional Explanations of Neurons

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints

[7:10] On Power Laws in Deep Ensembles

[7:20] Learning the Geometry of Wave-Based Imaging

[7:30] The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:30

[7:50] Sparse and Continuous Attention Mechanisms

[8:00] Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networks

[8:10] Directional convergence and alignment in deep learning

[8:20] Neural Controlled Differential Equations for Irregular Time Series

Q&A s 8:30-8:40

[8:30] Joint Q&A for Preceeding Spotlights

Break s 8:40-9:00

Break

(ends 9:00 AM)

Orals & Spotlights Track 29: Neuroscience [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Learning abstract structure for drawing by efficient motor program induction

[6:15] Non-reversible Gaussian processes for identifying latent dynamical structure in neural data

[6:30] Gibbs Sampling with People

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] Stable and expressive recurrent vision models

[7:10] Identifying Learning Rules From Neural Network Observables

[7:20] A new inference approach for training shallow and deep generalized linear models of noisy interacting neurons

[7:30] Modeling Shared responses in Neuroimaging Studies through MultiView ICA

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:30

[7:50] Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning

[8:00] Uncovering the Topology of Time-Varying fMRI Data using Cubical Persistence

[8:10] System Identification with Biophysical Constraints: A Circuit Model of the Inner Retina

[8:20] A meta-learning approach to (re)discover plasticity rules that carve a desired function into a neural network

Q&A s 8:30-8:40

[8:30] Joint Q&A for Preceeding Spotlights

Break s 8:40-9:00

Break

(ends 9:00 AM)

Orals & Spotlights Track 30: Optimization/Theory [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Black-Box Ripper: Copying black-box models using generative evolutionary algorithms

[6:15] Towards a Better Global Loss Landscape of GANs

[6:30] Online Sinkhorn: Optimal Transport distances from sample streams

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses

[7:10] Optimal Approximation - Smoothness Tradeoffs for Soft-Max Functions

[7:20] Conformal Symplectic and Relativistic Optimization

[7:30] Random Reshuffling is Not Always Better

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:30

[7:50] The Statistical Complexity of Early-Stopped Mirror Descent

[8:00] Overfitting Can Be Harmless for Basis Pursuit, But Only to a Degree

[8:10] Towards Problem-dependent Optimal Learning Rates

[8:20] On Uniform Convergence and Low-Norm Interpolation Learning

Q&A s 8:30-8:40

[8:30] Joint Q&A for Preceeding Spotlights

Break s 8:40-9:00

Break

(ends 9:00 AM)

Orals & Spotlights Track 31: Reinforcement Learning [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Robust-Adaptive Control of Linear Systems: beyond Quadratic Costs

[6:15] Self-Paced Deep Reinforcement Learning

[6:30] Leverage the Average: an Analysis of KL Regularization in Reinforcement Learning

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] Bandit Linear Control

[7:10] Neural Dynamic Policies for End-to-End Sensorimotor Learning

[7:20] Effective Diversity in Population Based Reinforcement Learning

[7:30] Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:30

[7:50] Reward Propagation Using Graph Convolutional Networks

[8:00] On the Convergence of Smooth Regularized Approximate Value Iteration Schemes

[8:10] Latent World Models For Intrinsically Motivated Exploration

[8:20] Learning to Play No-Press Diplomacy with Best Response Policy Iteration

Q&A s 8:30-8:40

[8:30] Joint Q&A for Preceeding Spotlights

Break s 8:40-9:00

Break

(ends 9:00 AM)

9 a.m.

Poster Session 6 [9:00-11:00]

Unsupervised Sound Separation Using Mixture Invariant Training

Neural Networks with Small Weights and Depth-Separation Barriers

The Implications of Local Correlation on Learning Some Deep Functions

Provably adaptive reinforcement learning in metric spaces

Instance Based Approximations to Profile Maximum Likelihood

Continual Learning of Control Primitives : Skill Discovery via Reset-Games

Unsupervised Semantic Aggregation and Deformable Template Matching for Semi-Supervised Learning

Multilabel Classification by Hierarchical Partitioning and Data-dependent Grouping

Transductive Information Maximization for Few-Shot Learning

Meta-Learning Requires Meta-Augmentation

Co-Tuning for Transfer Learning

What Makes for Good Views for Contrastive Learning?

Self-Supervised Relational Reasoning for Representation Learning

Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning

Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning

Supervised Contrastive Learning

Curriculum Learning by Dynamic Instance Hardness

SuperLoss: A Generic Loss for Robust Curriculum Learning

Neural Topographic Factor Analysis for fMRI Data

Self-supervised learning through the eyes of a child

Learnability with Indirect Supervision Signals

Learning from Label Proportions: A Mutual Contamination Framework

Learning identifiable and interpretable latent models of high-dimensional neural activity using pi-VAE

Identifying signal and noise structure in neural population activity with Gaussian process factor models

Neuronal Gaussian Process Regression

Estimating Fluctuations in Neural Representations of Uncertain Environments

Understanding spiking networks through convex optimization

Factorized Neural Processes for Neural Processes: K-Shot Prediction of Neural Responses

Efficient estimation of neural tuning during naturalistic behavior

A new inference approach for training shallow and deep generalized linear models of noisy interacting neurons

Optimal Adaptive Electrode Selection to Maximize Simultaneously Recorded Neuron Yield

Non-reversible Gaussian processes for identifying latent dynamical structure in neural data

Minimax Dynamics of Optimally Balanced Spiking Networks of Excitatory and Inhibitory Neurons

Predictive coding in balanced neural networks with noise, chaos and delays

Manifold GPLVMs for discovering non-Euclidean latent structure in neural data

Online Neural Connectivity Estimation with Noisy Group Testing

Recurrent Switching Dynamical Systems Models for Multiple Interacting Neural Populations

Rescuing neural spike train models from bad MLE

Flows for simultaneous manifold learning and density estimation

Multimodal Generative Learning Utilizing Jensen-Shannon-Divergence

SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows

User-Dependent Neural Sequence Models for Continuous-Time Event Data

Adversarially-learned Inference via an Ensemble of Discrete Undirected Graphical Models

Hierarchical Quantized Autoencoders

Riemannian Continuous Normalizing Flows

Efficient Learning of Generative Models via Finite-Difference Score Matching

Learning Latent Space Energy-Based Prior Model

Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective

VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data

Stochastic Normalizing Flows

Generative Neurosymbolic Machines

Fast and Flexible Temporal Point Processes with Triangular Maps

Deep Rao-Blackwellised Particle Filters for Time Series Forecasting

Neural Dynamic Policies for End-to-End Sensorimotor Learning

Critic Regularized Regression

Off-Policy Imitation Learning from Observations

Deep Inverse Q-learning with Constraints

Value-driven Hindsight Modelling

Effective Diversity in Population Based Reinforcement Learning

Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization

Reward Propagation Using Graph Convolutional Networks

PlanGAN: Model-based Planning With Sparse Rewards and Multiple Goals

Self-Paced Deep Reinforcement Learning

Memory Based Trajectory-conditioned Policies for Learning from Sparse Rewards

Learning to Utilize Shaping Rewards: A New Approach of Reward Shaping

f-GAIL: Learning f-Divergence for Generative Adversarial Imitation Learning

Strictly Batch Imitation Learning by Energy-based Distribution Matching

Meta-Gradient Reinforcement Learning with an Objective Discovered Online

Inverse Reinforcement Learning from a Gradient-based Learner

Regret Bounds without Lipschitz Continuity: Online Learning with Relative-Lipschitz Losses

Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses

Biased Stochastic First-Order Methods for Conditional Stochastic Optimization and Applications in Meta Learning

Tight Nonparametric Convergence Rates for Stochastic Gradient Descent under the Noiseless Linear Model

Exponential ergodicity of mirror-Langevin diffusions

Faster Wasserstein Distance Estimation with the Sinkhorn Divergence

Exploiting Higher Order Smoothness in Derivative-free Optimization and Continuous Bandits

The Statistical Complexity of Early-Stopped Mirror Descent

Statistical and Topological Properties of Sliced Probability Divergences

Sharper Generalization Bounds for Pairwise Learning

Can Implicit Bias Explain Generalization? Stochastic Convex Optimization as a Case Study

Asymptotic Guarantees for Generative Modeling Based on the Smooth Wasserstein Distance

Towards Problem-dependent Optimal Learning Rates

On Uniform Convergence and Low-Norm Interpolation Learning

Estimating weighted areas under the ROC curve

Generalization error in high-dimensional perceptrons: Approaching Bayes error with convex optimization

On Second Order Behaviour in Augmented Neural ODEs

Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints

Object-Centric Learning with Slot Attention

Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks

Probabilistic Time Series Forecasting with Shape and Temporal Diversity

A shooting formulation of deep learning

Training Linear Finite-State Machines

Benchmarking Deep Inverse Models over time, and the Neural-Adjoint method

Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations

Fast Transformers with Clustered Attention

SMYRF - Efficient Attention using Asymmetric Clustering

Sparse and Continuous Attention Mechanisms

Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows

Denoising Diffusion Probabilistic Models

Untangling tradeoffs between recurrence and self-attention in artificial neural networks

Neural Controlled Differential Equations for Irregular Time Series

Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphs

Unsupervised Joint k-node Graph Representations with Compositional Energy-Based Models

Pointer Graph Networks

Can Graph Neural Networks Count Substructures?

Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning

Graph Random Neural Networks for Semi-Supervised Learning on Graphs

Graph Contrastive Learning with Augmentations

Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks

Graph Stochastic Neural Networks for Semi-supervised Learning

DiffGCN: Graph Convolutional Networks via Differential Operators and Algebraic Multigrid Pooling

SAC: Accelerating and Structuring Self-Attention via Sparse Adaptive Connection

Curvature Regularization to Prevent Distortion in Graph Embedding

GCOMB: Learning Budget-constrained Combinatorial Algorithms over Billion-sized Graphs

Subgraph Neural Networks

PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks

Factor Graph Neural Networks

WOR and

$p$ 's: Sketches for

$\ell_p$ -Sampling Without Replacement

Statistical Guarantees of Distributed Nearest Neighbor Classification

Robust Persistence Diagrams using Reproducing Kernels

Regression with reject option and application to kNN

A Statistical Mechanics Framework for Task-Agnostic Sample Design in Machine Learning

Uncertainty Quantification for Inferring Hawkes Networks

Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains

SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks

A Stochastic Path Integral Differential EstimatoR Expectation Maximization Algorithm

Beyond Perturbations: Learning Guarantees with Arbitrary Adversarial Test Examples

Confidence sequences for sampling without replacement

Truthful Data Acquisition via Peer Prediction

Axioms for Learning from Pairwise Comparisons

Testing Determinantal Point Processes

Coded Sequential Matrix Multiplication For Straggler Mitigation

Functional Regularization for Representation Learning: A Unified Theoretical Perspective

Adaptive Sampling for Stochastic Risk-Averse Learning

High-Dimensional Sparse Linear Bandits

Adversarial Bandits with Corruptions

On Regret with Multiple Best Arms

Model Selection in Contextual Stochastic Bandit Problems

An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits

Adapting to Misspecification in Contextual Bandits

Leveraging Predictions in Smoothed Online Convex Optimization via Gradient-based Algorithms

Bandit Linear Control

Robust-Adaptive Control of Linear Systems: beyond Quadratic Costs

On the Convergence of Smooth Regularized Approximate Value Iteration Schemes

Pontryagin Differentiable Programming: An End-to-End Learning and Control Framework

Leverage the Average: an Analysis of KL Regularization in Reinforcement Learning

Implicit Distributional Reinforcement Learning

Small Nash Equilibrium Certificates in Very Large Games

Contextual Games: Multi-Agent Learning with Side Information

Recursive Inference for Variational Autoencoders

Bayesian Pseudocoresets

Variational Bayesian Monte Carlo with Noisy Likelihoods

Bayesian Probabilistic Numerical Integration with Tree-Based Models

Beyond the Mean-Field: Structured Deep Gaussian Processes Improve the Predictive Uncertainties

Fast Matrix Square Roots with Applications to Gaussian Processes and Bayesian Optimization

Analytical Probability Distributions and Exact Expectation-Maximization for Deep Generative Networks

Decentralized Langevin Dynamics for Bayesian Learning

Hamiltonian Monte Carlo using an adjoint-differentiated Laplace approximation: Bayesian inference for latent Gaussian models and beyond

Decision-Making with Auto-Encoding Variational Bayes

Robust, Accurate Stochastic Optimization for Variational Inference

Advances in Black-Box VI: Normalizing Flows, Importance Weighting, and Optimization

Efficient Low Rank Gaussian Variational Inference for Neural Networks

Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations

Markovian Score Climbing: Variational Inference with KL(p||q)

Projected Stein Variational Gradient Descent

Lipschitz Bounds and Provably Robust Training by Laplacian Smoothing

SnapBoost: A Heterogeneous Boosting Machine

The Wasserstein Proximal Gradient Algorithm

Unbalanced Sobolev Descent

Steering Distortions to Preserve Classes and Neighbors in Supervised Dimensionality Reduction

Multiparameter Persistence Image for Topological Machine Learning

Learning with Differentiable Pertubed Optimizers

Learning with Optimized Random Features: Exponential Speedup by Quantum Machine Learning without Sparsity and Low-Rank Assumptions

Learning outside the Black-Box: The pursuit of interpretable models

Variance Reduction via Accelerated Dual Averaging for Finite-Sum Optimization

Random Reshuffling is Not Always Better

Optimistic Dual Extrapolation for Coherent Non-monotone Variational Inequalities

Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters

Online Sinkhorn: Optimal Transport distances from sample streams

A Non-Asymptotic Analysis for Stein Variational Gradient Descent

SVGD as a kernelized Wasserstein gradient flow of the chi-squared divergence

Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting

The NetHack Learning Environment

Discovering Reinforcement Learning Algorithms

Latent World Models For Intrinsically Motivated Exploration

Promoting Coordination through Policy Regularization in Multi-Agent Deep Reinforcement Learning

Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning

Learning to Incentivize Other Learning Agents

Calibration of Shared Equilibria in General Sum Partially Observable Markov Games

A game-theoretic analysis of networked system control for common-pool resource management using multi-agent reinforcement learning

Learning to Play No-Press Diplomacy with Best Response Policy Iteration

A Boolean Task Algebra for Reinforcement Learning

Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Control

Munchausen Reinforcement Learning

Information-theoretic Task Selection for Meta-Reinforcement Learning

Automatic Curriculum Learning through Value Disagreement

Combining Deep Reinforcement Learning and Search for Imperfect-Information Games

Matrix Completion with Quantified Uncertainty through Low Rank Gaussian Copula

Learning to Prove Theorems by Learning to Generate Theorems

CHIP: A Hawkes Process Model for Continuous-time Networks with Scalable and Consistent Estimation

Probabilistic Inference with Algebraic Constraints: Theoretical Limits and Practical Approximations

Reasoning about Uncertainties in Discrete-Time Dynamical Systems using Polynomial Forms.

Taming Discrete Integration via the Boon of Dimensionality

Belief Propagation Neural Networks

Scalable Belief Propagation via Relaxed Scheduling

Probabilistic Circuits for Variational Inference in Discrete Graphical Models

Towards Scalable Bayesian Learning of Causal DAGs

A Novel Approach for Constrained Optimization in Graphical Models

DAGs with No Fears: A Closer Look at Continuous Optimization for Learning Bayesian Networks

Factor Graph Grammars

Efficient Learning of Discrete Graphical Models

Online Bayesian Goal Inference for Boundedly Rational Planning Agents

Greedy inference with structure-exploiting lazy maps

Biologically Inspired Mechanisms for Adversarial Robustness

Bayes Consistency vs. H-Consistency: The Interplay between Surrogate Loss Functions and the Scoring Function Class

Training Normalizing Flows with the Information Bottleneck for Competitive Generative Classification

Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes

A Unified View of Label Shift Estimation

Calibrating Deep Neural Networks using Focal Loss

Distribution-free binary classification: prediction sets, confidence intervals and calibration

Log-Likelihood Ratio Minimizing Flows: Towards Robust and Quantifiable Neural Distribution Alignment

Your GAN is Secretly an Energy-based Model and You Should Use Discriminator Driven Latent Sampling

Exchangeable Neural ODE for Set Modeling

Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Features

Further Analysis of Outlier Detection with Deep Generative Models

Sample Complexity of Uniform Convergence for Multicalibration

Certifiably Adversarially Robust Detection of Out-of-Distribution Data

Can I Trust My Fairness Metric? Assessing Fairness with Unlabeled Data and Bayesian Inference

Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examples

Reducing Adversarially Robust Learning to Non-Robust PAC Learning

Tensor Completion Made Practical

Online Matrix Completion with Side Information

Truncated Linear Regression in High Dimensions

Finer Metagenomic Reconstruction via Biodiversity Optimization

Implicit Regularization in Deep Learning May Not Be Explainable by Norms

On the Tightness of Semidefinite Relaxations for Certifying Robustness to Adversarial Examples

Towards a Better Global Loss Landscape of GANs

Implicit Regularization and Convergence for Weight Normalization

Most ReLU Networks Suffer from

$\ell^2$ Adversarial Perturbations

Geometric Exploration for Online Control

The Smoothed Possibility of Social Choice

Optimally Deceiving a Learning Leader in Stackelberg Games

Explainable Voting

Optimization and Generalization of Shallow Neural Networks with Quadratic Activation Functions

Overfitting Can Be Harmless for Basis Pursuit, But Only to a Degree

A Benchmark for Systematic Generalization in Grounded Language Understanding

Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures

Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks

Meta-Learning through Hebbian Plasticity in Random Networks

Stable and expressive recurrent vision models

Identifying Learning Rules From Neural Network Observables

Deep active inference agents using Monte-Carlo methods

Learning Compositional Rules via Neural Program Synthesis

A Local Temporal Difference Code for Distributional Reinforcement Learning

Inferring learning rules from animal decision-making

A Biologically Plausible Neural Network for Slow Feature Analysis

R-learning in actor-critic model offers a biologically relevant mechanism for sequential decision-making

Deep Graph Pose: a semi-supervised deep graphical model for improved animal pose tracking

Characterizing emergent representations in a space of candidate learning rules for deep networks

A simple normative network approximates local non-Hebbian learning in the cortex

A meta-learning approach to (re)discover plasticity rules that carve a desired function into a neural network

Detection as Regression: Certified Object Detection with Median Smoothing

Certifying Confidence via Randomized Smoothing

Reliable Graph Neural Networks via Robust Aggregation

PLLay: Efficient Topological Layer based on Persistent Landscapes

Network Diffusions via Neural Mean-Field Dynamics

Learning the Geometry of Wave-Based Imaging

Neuron Shapley: Discovering the Responsible Neurons

Certified Robustness of Graph Convolution Networks for Graph Classification under Topological Attacks

Sharp Representation Theorems for ReLU Networks with Precise Dependence on Depth

Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networks

Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder

Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining

Discovering Symbolic Models from Deep Learning with Inductive Biases

Compositional Explanations of Neurons

Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond

Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality

Telescoping Density-Ratio Estimation

On Testing of Samplers

Path Sample-Analytic Gradient Estimators for Stochastic Binary Networks

Deep Direct Likelihood Knockoffs

Generalised Bayesian Filtering via Sequential Monte Carlo

Feature Shift Detection: Localizing Which Features Have Shifted via Conditional Distribution Tests

Bayesian Optimization of Risk Measures

Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimization

Variance reduction for Random Coordinate Descent-Langevin Monte Carlo

A Contour Stochastic Gradient Langevin Dynamics Algorithm for Simulations of Multi-modal Distributions

Sequential Bayesian Experimental Design with Variable Cost Structure

Asymptotically Optimal Exact Minibatch Metropolis-Hastings

Primal Dual Interpretation of the Proximal Stochastic Gradient Langevin Algorithm

Replica-Exchange Nos\'e-Hoover Dynamics for Bayesian Learning on Large Datasets

Stein Self-Repulsive Dynamics: Benefits From Past Samples

Neural Bridge Sampling for Evaluating Safety-Critical Autonomous Systems

Sparse Spectrum Warped Input Measures for Nonstationary Kernel Learning

Bootstrapping neural processes

Sparse Learning with CART

Smooth And Consistent Probabilistic Regression Trees

Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness

Bayesian Deep Ensembles via the Neural Tangent Kernel

Predictive inference is free with the jackknife+-after-bootstrap

Hyperparameter Ensembles for Robustness and Uncertainty Quantification

Depth Uncertainty in Neural Networks

A Bayesian Perspective on Training Speed and Model Selection

Learning under Model Misspecification: Applications to Variational and Ensemble methods

Counterfactual Predictions under Runtime Confounding

Matérn Gaussian Processes on Riemannian Manifolds

Stationary Activations for Uncertainty Calibration in Deep Learning

Task-Agnostic Amortized Inference of Gaussian Process Hyperparameters

On the Expressiveness of Approximate Inference in Bayesian Neural Networks

The Strong Screening Rule for SLOPE

Co-exposure Maximization in Online Social Networks

Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev

Memory-Efficient Learning of Stable Linear Dynamical Systems for Prediction and Control

MinMax Methods for Optimal Transport and Beyond: Regularization, Approximation and Numerics

Semialgebraic Optimization for Lipschitz Constants of ReLU Networks

Parabolic Approximation Line Search for DNNs

Batch normalization provably avoids ranks collapse for randomly initialised deep networks

Breaking Reversibility Accelerates Langevin Dynamics for Non-Convex Optimization

Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization

Conic Descent and its Application to Memory-efficient Optimization over Positive Semidefinite Matrices

A mean-field analysis of two-player zero-sum games

Robust Federated Learning: The Case of Affine Distribution Shifts

Learning compositional functions via multiplicative weight updates

Stochastic Optimization for Performative Prediction

Conformal Symplectic and Relativistic Optimization

On Power Laws in Deep Ensembles

Residual Distillation: Towards Portable Deep Neural Networks without Shortcuts

Bayesian Deep Learning and a Probabilistic Perspective of Generalization

Self-Distillation as Instance-Specific Label Smoothing

On the training dynamics of deep networks with

$L_2$ regularization

Reconciling Modern Deep Learning with Traditional Optimization Analyses: The Intrinsic Learning Rate

Batch Normalization Biases Residual Blocks Towards the Identity Function in Deep Networks

Numerically Solving Parametric Families of High-Dimensional Kolmogorov Partial Differential Equations via Deep Learning

Bad Global Minima Exist and SGD Can Reach Them

The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks

Ensemble Distillation for Robust Model Fusion in Federated Learning

On Warm-Starting Neural Network Training

Predicting Training Time Without Training

Directional convergence and alignment in deep learning

Black-Box Ripper: Copying black-box models using generative evolutionary algorithms

Consistent feature selection for analytic deep neural networks

Fast Adversarial Robustness Certification of Nearest Prototype Classifiers for Arbitrary Seminorms

Sampling from a k-DPP without looking at all items

Optimal Learning from Verified Training Data

Empirical Likelihood for Contextual Bandits

Sufficient dimension reduction for classification using principal optimal transport direction

The Advantage of Conditional Meta-Learning for Biased Regularization and Fine Tuning

On the Role of Sparsity and DAG Constraints for Learning Linear DAGs

Listening to Sounds of Silence for Speech Denoising

A Convolutional Auto-Encoder for Haplotype Assembly and Viral Quasispecies Reconstruction

Geometric All-way Boolean Tensor Decomposition

A novel variational form of the Schatten-

$p$ quasi-norm

Distributionally Robust Parametric Maximum Likelihood Estimation

Adaptive Probing Policies for Shortest Path Routing

Optimal Approximation - Smoothness Tradeoffs for Soft-Max Functions

Content Provider Dynamics and Coordination in Recommendation Ecosystems

Non-parametric Models for Non-negative Functions

Program Synthesis with Pragmatic Communication

Detecting Interactions from Neural Networks via Topological Analysis

Learning efficient task-dependent representations with synaptic plasticity

Modeling Shared responses in Neuroimaging Studies through MultiView ICA

Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning

Uncovering the Topology of Time-Varying fMRI Data using Cubical Persistence

Interpretable multi-timescale models for predicting fMRI responses to continuous natural speech

Learning abstract structure for drawing by efficient motor program induction

Mutual exclusivity as a challenge for deep neural networks

Gibbs Sampling with People

Learning sparse codes from compressed representations with biologically plausible local wiring constraints

Shared Space Transfer Learning for analyzing multi-site fMRI data

Modeling Task Effects on Meaning Representation in the Brain via Zero-Shot MEG Prediction

System Identification with Biophysical Constraints: A Circuit Model of the Inner Retina

An Unsupervised Information-Theoretic Perceptual Quality Metric

Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency

CoMIR: Contrastive Multimodal Image Representation for Registration

CrossTransformers: spatially-aware few-shot transfer

Contrastive learning of global and local features for medical image segmentation with limited annotations

3D Self-Supervised Methods for Medical Imaging

Unsupervised Learning of Dense Visual Representations

Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biases

Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning

Unsupervised Learning of Visual Features by Contrasting Cluster Assignments

LoCo: Local Contrastive Representation Learning

Self-Adaptively Learning to Demoiré from Focused and Defocused Image Pairs

Noise2Same: Optimizing A Self-Supervised Bound for Image Denoising

Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization

Differentiable Augmentation for Data-Efficient GAN Training

Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection

ContraGAN: Contrastive Learning for Conditional Image Generation

Inverting Gradients - How easy is it to break privacy in federated learning?

Principal Neighbourhood Aggregation for Graph Nets

Learning Graph Structure With A Finite-State Automaton Layer

Graph Cross Networks with Vertex Infomax Pooling

How hard is to distinguish graphs with graph neural networks?

Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings

COPT: Coordinated Optimal Transport on Graphs

Building powerful and equivariant graph neural networks with structural message-passing

Rethinking pooling in graph neural networks

Random Walk Graph Neural Networks

Path Integral Based Convolution and Pooling for Graph Neural Networks

Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings

Towards Deeper Graph Neural Networks with Differentiable Group Normalization

Graphon Neural Networks and the Transferability of Graph Neural Networks

Convergence and Stability of Graph Convolutional Networks on Large Random Graphs

GNNGuard: Defending Graph Neural Networks against Adversarial Attacks

Parameterized Explainer for Graph Neural Network

Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learning

(ends 11:00 AM)

noon

Affinity Workshop:

Indigenous in AI

(ends 2:10 PM)

Tutorial:

(Track1) Federated Learning and Analytics: Industry Meets Academia Q&A

(ends 12:50 PM)

1 p.m.

Tutorial:

(Track3) Policy Optimization in Reinforcement Learning Q&A

(ends 1:50 PM)

4 p.m.

Town Hall:

NeurIPS Town Hall

(duration 1.0 hr)

5 p.m.

Invited Talk:

The Genomic Bottleneck: A Lesson from Biology

Anthony M Zador

(ends 7:00 PM)

6 p.m.

Orals & Spotlights Track 32: Optimization [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Effective Dimension Adaptive Sketching Methods for Faster Regularized Least-Squares Optimization

[6:15] The Primal-Dual method for Learning Augmented Algorithms

[6:30] Fully Dynamic Algorithm for Constrained Submodular Optimization

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] Submodular Maximization Through Barrier Functions

[7:10] Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method

[7:20] A Single Recipe for Online Submodular Maximization with Adversarial or Stochastic Constraints

[7:30] How many samples is a good initial point worth in Low-rank Matrix Recovery?

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:30

[7:50] Projection Robust Wasserstein Distance and Riemannian Optimization

[8:00] A Continuous-Time Mirror Descent Approach to Sparse Phase Retrieval

[8:10] SGD with shuffling: optimal rates without component convexity and large epoch requirements

[8:20] No-Regret Learning and Mixed Nash Equilibria: They Do Not Mix

Q&A s 8:30-8:40

[8:30] Joint Q&A for Preceeding Spotlights

Break s 8:40-9:00

Break

(ends 9:00 PM)

Orals & Spotlights Track 33: Health/AutoML/(Soft|Hard)ware [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Theory-Inspired Path-Regularized Differential Network Architecture Search

[6:15] Improved Variational Bayesian Phylogenetic Inference with Normalizing Flows

[6:30] Transferable Graph Optimizers for ML Compilers

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] A Study on Encodings for Neural Architecture Search

[7:10] Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding

[7:20] Evolving Normalization-Activation Layers

[7:30] Open Graph Benchmark: Datasets for Machine Learning on Graphs

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:20

[7:50] Nimble: Lightweight and Parallel GPU Task Scheduling for Deep Learning

[8:00] MCUNet: Tiny Deep Learning on IoT Devices

[8:10] Computing Valid p-value for Optimal Changepoint by Selective Inference using Dynamic Programming

Q&A s 8:20-8:30

[8:20] Joint Q&A for Preceeding Spotlights

Break s 8:30-9:00

Break

(ends 9:00 PM)

Orals & Spotlights Track 34: Deep Learning [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Is normalization indispensable for training deep neural network?

[6:15] Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks

[6:30] Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] Generalization bound of globally optimal non-convex neural network training: Transportation map estimation by infinite dimensional Langevin dynamics

[7:10] Kernel Based Progressive Distillation for Adder Neural Networks

[7:20] What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation

[7:30] Collegial Ensembles

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:30

[7:50] Finite Versus Infinite Neural Networks: an Empirical Study

[8:00] Estimating Training Data Influence by Tracing Gradient Descent

[8:10] AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients

[8:20] Part-dependent Label Noise: Towards Instance-dependent Label Noise

Q&A s 8:30-8:40

[8:30] Joint Q&A for Preceeding Spotlights

Break s 8:40-9:00

Break

(ends 9:00 PM)

Orals & Spotlights Track 35: Neuroscience/Probabilistic [6:00-9:00]

Each Oral includes Q&A
Spotlights have joint Q&As

Oral s 6:00-6:45

[6:00] Point process models for sequence detection in high-dimensional neural spike trains

[6:15] Reconstructing Perceptive Images from Brain Activity by Shape-Semantic GAN

[6:30] A mathematical theory of cooperative communication

Break s 6:45-7:00

Break

Spotlight s 7:00-7:40

[7:00] Learning Some Popular Gaussian Graphical Models without Condition Number Bounds

[7:10] Sinkhorn Natural Gradient for Generative Models

[7:20] NVAE: A Deep Hierarchical Variational Autoencoder

[7:30] Reciprocal Adversarial Learning via Characteristic Functions

Q&A s 7:40-7:50

[7:40] Joint Q&A for Preceeding Spotlights

Spotlight s 7:50-8:20

[7:50] Incorporating Interpretable Output Constraints in Bayesian Neural Networks

[8:00] Baxter Permutation Process

[8:10] Flexible mean field variational inference using mixtures of non-overlapping exponential families

Q&A s 8:20-8:30

[8:20] Joint Q&A for Preceeding Spotlights

Break s 8:30-9:00

Break

(ends 9:00 PM)

9 p.m.

Poster Session 7 [9:00-11:00]

Linear-Sample Learning of Low-Rank Distributions

Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification

Multi-label classification: do Hamming loss and subset accuracy really conflict with each other?

Generalization Bound of Gradient Descent for Non-Convex Metric Learning

On the Optimal Weighted

$\ell_2$ Regularization in Overparameterized Linear Regression

Learning to Approximate a Bregman Divergence

Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks

Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel

Learning to solve TV regularised problems with unrolled algorithms

Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method

Neural Networks Learning and Memorization with (almost) no Over-Parameterization

From Boltzmann Machines to Neural Networks and Back Again

Learning Some Popular Gaussian Graphical Models without Condition Number Bounds

Fixed-Support Wasserstein Barycenters: Computational Hardness and Fast Algorithm

Projection Robust Wasserstein Distance and Riemannian Optimization

Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View

Minimax Bounds for Generalized Linear Models

Generalization bound of globally optimal non-convex neural network training: Transportation map estimation by infinite dimensional Langevin dynamics

Deep reconstruction of strange attractors from time series

STEER : Simple Temporal Regularization For Neural ODE

Learning Manifold Implicitly via Explicit Heat-Kernel Learning

Better Set Representations For Relational Reasoning

Intra Order-preserving Functions for Calibration of Multi-Class Neural Networks

Model Inversion Networks for Model-Based Optimization

Variational Amodal Object Completion

Low Distortion Block-Resampling with Spatially Stochastic Networks

Understanding Deep Architecture with Reasoning Layer

AdaTune: Adaptive Tensor Program Compilation Made Efficient

CircleGAN: Generative Adversarial Learning across Spherical Circles

SoftFlow: Probabilistic Framework for Normalizing Flow on Manifolds

Improved Techniques for Training Score-Based Generative Models

UDH: Universal Deep Hiding for Steganography, Watermarking, and Light Field Messaging

Deep Archimedean Copulas

Constraining Variational Inference with Geometric Jensen-Shannon Divergence

CO-Optimal Transport

OTLDA: A Geometry-aware Optimal Transport Approach for Topic Modeling

Robust Recursive Partitioning for Heterogeneous Treatment Effects with Uncertainty Quantification

Computing Valid p-value for Optimal Changepoint by Selective Inference using Dynamic Programming

Improved Variational Bayesian Phylogenetic Inference with Normalizing Flows

HM-ANN: Efficient Billion-Point Nearest Neighbor Search on Heterogeneous Memory

Noise-Contrastive Estimation for Multivariate Point Processes

Adaptive Learned Bloom Filter (Ada-BF): Efficient Utilization of the Classifier with Application to Real-Time Information Filtering on the Web

Nimble: Lightweight and Parallel GPU Task Scheduling for Deep Learning

Baxter Permutation Process

A mathematical theory of cooperative communication

All your loss are belong to Bayes

The Potts-Ising model for discrete multivariate data

Bidirectional Convolutional Poisson Gamma Dynamical Systems

Variational Bayesian Unlearning

Theory-Inspired Path-Regularized Differential Network Architecture Search

Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search

Differentiable Neural Architecture Search in Equivalent Space with Exploration Enhancement

AutoBSS: An Efficient Algorithm for Block Stacking Style Search

Semi-Supervised Neural Architecture Search

Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?

A Study on Encodings for Neural Architecture Search

Evolving Normalization-Activation Layers

Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding

Auto Learning Attention

Transferable Graph Optimizers for ML Compilers

Adapting Neural Architectures Between Domains

Revisiting Parameter Sharing for Automatic Neural Channel Number Search

Neuron-level Structured Pruning using Polarization Regularizer

HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks

MCUNet: Tiny Deep Learning on IoT Devices

Compressing Images by Encoding Their Latent Representations with Relative Entropy Coding

Bi-level Score Matching for Learning Energy-based Latent Variable Models

NVAE: A Deep Hierarchical Variational Autoencoder

Reciprocal Adversarial Learning via Characteristic Functions

Stochastic Stein Discrepancies

Hierarchical Gaussian Process Priors for Bayesian Neural Network Weights

Incorporating Interpretable Output Constraints in Bayesian Neural Networks

Quantile Propagation for Wasserstein-Approximate Gaussian Processes

Mixed Hamiltonian Monte Carlo for Mixed Discrete and Continuous Variables

Walsh-Hadamard Variational Inference for Bayesian Deep Learning

f-Divergence Variational Inference

Flexible mean field variational inference using mixtures of non-overlapping exponential families

On the Ergodicity, Bias and Asymptotic Normality of Randomized Midpoint Sampling Method

Improving Online Rent-or-Buy Algorithms with Sequential Decision Making and ML Predictions

Community detection using fast low-cardinality semidefinite programming 

Online Optimization with Memory and Competitive Control

Simple and Fast Algorithm for Binary Integer and Online Linear Programming

A Single Recipe for Online Submodular Maximization with Adversarial or Stochastic Constraints

Online Convex Optimization Over Erdos-Renyi Random Networks

Thunder: a Fast Coordinate Selection Solver for Sparse Learning

Deterministic Approximation for Submodular Maximization over a Matroid in Nearly Linear Time

The Primal-Dual method for Learning Augmented Algorithms

Fully Dynamic Algorithm for Constrained Submodular Optimization

Submodular Maximization Through Barrier Functions

Improved Algorithms for Online Submodular Maximization via First-order Regret Bounds

Robust Sequence Submodular Maximization

Continuous Submodular Maximization: Beyond DR-Submodularity

Efficient Online Learning of Optimal Rankings: Dimensionality Reduction via Gradient Descent

Towards More Practical Adversarial Attacks on Graph Neural Networks

Boundary thickness and robustness in learning models

Exploiting weakly supervised visual patterns to learn from partial annotations

Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning

Part-dependent Label Noise: Towards Instance-dependent Label Noise

Digraph Inception Convolutional Networks

What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation

Self-Adaptive Training: beyond Empirical Risk Minimization

Debugging Tests for Model Explanations

Point process models for sequence detection in high-dimensional neural spike trains

Lamina-specific neuronal properties promote robust, stable signal propagation in feedforward networks

Reconstructing Perceptive Images from Brain Activity by Shape-Semantic GAN

High-contrast “gaudy” images improve the training of deep neural network models of visual cortex

Weakly-Supervised Reinforcement Learning for Controllable Behavior

Predictive Information Accelerates Learning in RL

The route to chaos in routing games: When is price of anarchy too optimistic?

Graph Meta Learning via Local Subgraphs

Graph Information Bottleneck

Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous GNNs

Tree! I am no Tree! I am a low dimensional Hyperbolic Embedding

Scalable Graph Neural Networks via Bidirectional Propagation

Neural Message Passing for Multi-Relational Ordered and Recursive Hypergraphs

A graph similarity for deep learning

Implicit Graph Neural Networks

Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs

Disentangling Human Error from Ground Truth in Segmentation of Medical Images

Graph Policy Network for Transferable Active Learning on Graphs

Open Graph Benchmark: Datasets for Machine Learning on Graphs

Factorizable Graph Convolutional Networks

Graduated Assignment for Joint Multi-Graph Matching and Clustering with Application to Unsupervised Graph Matching Network Learning

Natural Graph Networks

Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks

Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian

Sinkhorn Natural Gradient for Generative Models

Nonconvex Sparse Graph Learning under Laplacian Constrained Graphical Model

How many samples is a good initial point worth in Low-rank Matrix Recovery?

Effective Dimension Adaptive Sketching Methods for Faster Regularized Least-Squares Optimization

Faster Randomized Infeasible Interior Point Methods for Tall/Wide Linear Programs

Debiasing Distributed Second Order Optimization with Surrogate Sketching and Scaled Regularization

Tight last-iterate convergence rates for no-regret learning in multi-player games

A General Large Neighborhood Search Framework for Solving Integer Linear Programs

Sinkhorn Barycenter via Functional Gradient Descent

Improved Analysis of Clipping Algorithms for Non-convex Optimization

A Continuous-Time Mirror Descent Approach to Sparse Phase Retrieval

Federated Accelerated Stochastic Gradient Descent

AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients

SGD with shuffling: optimal rates without component convexity and large epoch requirements

No-Regret Learning and Mixed Nash Equilibria: They Do Not Mix

Generalized Leverage Score Sampling for Neural Networks

Passport-aware Normalization for Deep Model Protection

Model Rubik’s Cube: Twisting Resolution, Depth and Width for TinyNets

Neural Networks Fail to Learn Periodic Functions and How to Fix It

Finite Versus Infinite Neural Networks: an Empirical Study

Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks

Collegial Ensembles

Accelerating Training of Transformer-Based Language Models with Progressive Layer Dropping

Top-k Training of GANs: Improving GAN Performance by Throwing Away Bad Samples

Towards Theoretically Understanding Why Sgd Generalizes Better Than Adam in Deep Learning

A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks

Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response Jacobians

Coresets for Robust Training of Deep Neural Networks against Noisy Labels

Learning Deep Attribution Priors Based On Prior Knowledge

Estimating Training Data Influence by Tracing Gradient Descent

Escaping Saddle-Point Faster under Interpolation-like Conditions

Learning Loss for Test-Time Augmentation

Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Experts

MMA Regularization: Decorrelating Weights of Neural Networks by Maximizing the Minimal Angles

The Dilemma of TriHard Loss and an Element-Weighted TriHard Loss for Person Re-Identification

Is normalization indispensable for training deep neural network?

SCOP: Scientific Control for Reliable Neural Network Pruning

Train-by-Reconnect: Decoupling Locations of Weights from Their Values

Deep Metric Learning with Spherical Embedding

Kernel Based Progressive Distillation for Adder Neural Networks

Top-KAST: Top-K Always Sparse Training

Task-Oriented Feature Distillation

Rotated Binary Neural Network

Agree to Disagree: Adaptive Ensemble Knowledge Distillation in Gradient Space

Sparse Weight Activation Training

Recurrent Quantum Neural Networks

Efficient Variational Inference for Sparse Deep Learning with Theoretical Guarantee

(ends 11:00 PM)

FRI 11 DEC

midnight

Workshops Fri [12:00-2:59]

Workshop s 11:00-4:00

Topological Data Analysis and Beyond

Privacy Preserving Machine Learning - PriML and PPML Joint Edition

Tackling Climate Change with ML

Meta-Learning

OPT2020: Optimization for Machine Learning

Advances and Opportunities: Machine Learning for Education

Differential Geometry meets Deep Learning (DiffGeo4DL)

Workshop on Dataset Curation and Security

Machine Learning for Health (ML4H): Advancing Healthcare for All

Learning Meaningful Representations of Life (LMRL.org)

First Workshop on Quantum Tensor Networks in Machine Learning

Human in the loop dialogue systems

The pre-registration experiment: an alternative publication model for machine learning research

Differentiable computer vision, graphics, and physics in machine learning

Self-Supervised Learning for Speech and Audio Processing

Causal Discovery and Causality-Inspired Machine Learning

Machine Learning and the Physical Sciences

Resistance AI Workshop

ML Competitions at the Grassroots (CiML 2020)

3rd Robot Learning Workshop

Workshop on Deep Learning and Inverse Problems

Machine Learning for Autonomous Driving

Competition Track Friday

Object Representations for Learning and Reasoning

Fair AI in Finance

Crowd Science Workshop: Remoteness, Fairness, and Mechanisms as Challenges of Data Supply by Humans for Automation

ML Retrospectives, Surveys & Meta-Analyses (ML-RSA)

Deep Reinforcement Learning

KR2ML - Knowledge Representation and Reasoning Meets Machine Learning

BabyMind: How Babies Learn and How Machines Can Imitate

Machine Learning for Economic Policy

(ends 2:59 PM)

4 p.m.

Workshops Sat [4:00-3:59]

Workshop s 1:00-6:30

Algorithmic Fairness through the Lens of Causality and Interpretability

Medical Imaging Meets NeurIPS

Learning Meets Combinatorial Algorithms

Machine Learning for the Developing World (ML4D): Improving Resilience

Biological and Artificial Reinforcement Learning

I Can’t Believe It’s Not Better! Bridging the gap between theory and empiricism in probabilistic machine learning

Machine Learning for Engineering Modeling, Simulation and Design

Machine Learning for Creativity and Design 4.0

Cooperative AI

Navigating the Broader Impacts of AI Research

Machine Learning for Molecules

Beyond BackPropagation: Novel Ideas for Training Neural Architectures

Wordplay: When Language Meets Games

MLPH: Machine Learning in Public Health

Interpretable Inductive Biases and Physically Structured Learning

AI for Earth Sciences

Talking to Strangers: Zero-Shot Emergent Communication

Machine Learning for Mobile Health

Shared Visual Representations in Human and Machine Intelligence (SVRHM)

Second Workshop on AI for Humanitarian Assistance and Disaster Response

Consequential Decisions in Dynamic Environments

Competition Track Saturday

Machine Learning for Structural Biology

HAMLETS: Human And Model in the Loop Evaluation and Training Strategies

International Workshop on Scalability, Privacy, and Security in Federated Learning (SpicyFL 2020)

Workshop on Computer Assisted Programming (CAP)

The Challenges of Real World Reinforcement Learning

Self-Supervised Learning -- Theory and Practice

Offline Reinforcement Learning

Machine Learning for Systems

Deep Learning through Information Geometry

(ends 3:59 PM)