Downloads 2019
Number of events: 1528
- A Bayesian Theory of Conformity in Collective Decision Making
- A Benchmark for Interpretability Methods in Deep Neural Networks
- Abstraction based Output Range Analysis for Neural Networks
- Abstract Reasoning with Distracting Features
- Accelerating Rescaled Gradient Descent: Fast Optimization of Smooth Functions
- Acceleration via Symplectic Discretization of High-Resolution Differential Equations
- Accurate Layerwise Interpretable Competence Estimation
- Accurate, reliable and fast robustness evaluation
- Accurate Uncertainty Estimation and Decomposition in Ensemble Learning
- A Communication Efficient Stochastic Multi-Block Alternating Direction Method of Multipliers
- A Composable Specification Language for Reinforcement Learning Tasks
- A Condition Number for Joint Optimization of Cycle-Consistent Networks
- A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks
- A coupled autoencoder approach for multi-modal analysis of cell types
- Adapting Neural Networks for the Estimation of Treatment Effects
- Adaptive Auxiliary Task Weighting for Reinforcement Learning
- Adaptive Cross-Modal Few-shot Learning
- Adaptive Density Estimation for Generative Models
- Adaptive GNN for Image Analysis and Editing
- Adaptive Gradient-Based Meta-Learning Methods
- Adaptive Influence Maximization with Myopic Feedback
- Adaptively Aligned Image Captioning via Adaptive Attention Time
- Adaptive Sequence Submodularity
- Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates
- ADDIS: an adaptive discarding algorithm for online FDR control with conservative nulls
- Addressing Failure Prediction by Learning Model Confidence
- Addressing Sample Complexity in Visual Tasks Using HER and Hallucinatory GANs
- A Debiased MDI Feature Importance Measure for Random Forests
- A Direct tilde{O}(1/epsilon) Iteration Parallel Algorithm for Optimal Transport
- A Domain Agnostic Measure for Monitoring and Evaluating GANs
- Adversarial Examples Are Not Bugs, They Are Features
- Adversarial Fisher Vectors for Unsupervised Representation Learning
- Adversarial Music: Real world Audio Adversary against Wake-word Detection System
- Adversarial Robustness through Local Linearization
- Adversarial Self-Defense for Cycle-Consistent GANs
- Adversarial Training and Robustness for Multiple Perturbations
- Adversarial training for free!
- A Family of Robust Stochastic Operators for Reinforcement Learning
- A First-Order Algorithmic Framework for Wasserstein Distributionally Robust Logistic Regression
- A Flexible Generative Framework for Graph-based Semi-supervised Learning
- A Fourier Perspective on Model Robustness in Computer Vision
- A Game Theoretic Approach to Class-wise Selective Rationalization
- AGEM: Solving Linear Inverse Problems via Deep Priors and Sampling
- Agency + Automation: Designing Artificial Intelligence into Interactive Systems
- A General Framework for Symmetric Property Estimation
- A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation
- A General Theory of Equivariant CNNs on Homogeneous Spaces
- A Generic Acceleration Framework for Stochastic Composite Optimization
- A Geometric Perspective on Optimal Representations for Reinforcement Learning
- A Graph Theoretic Additive Approximation of Optimal Transport
- A Graph Theoretic Framework of Recomputation Algorithms for Memory-Efficient Backpropagation
- AIDEme: An active learning based system for interactive exploration of large datasets
- AI for Humanitarian Assistance and Disaster Response
- AI in Two-sided Ride-sharing Marketplace
- A Kernel Loss for Solving the Bellman Equation
- A Latent Variational Framework for Stochastic Optimization
- Algorithm-Dependent Generalization Bounds for Overparameterized Deep Residual Networks
- Algorithmic Analysis and Statistical Estimation of SLOPE via Approximate Message Passing
- Algorithmic Guarantees for Inverse Imaging with Untrained Network Priors
- Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations
- A Linearly Convergent Method for Non-Smooth Non-Convex Optimization on the Grassmannian with Applications to Robust Subspace and Dictionary Learning
- A Linearly Convergent Proximal Gradient Algorithm for Decentralized Optimization
- A Little Is Enough: Circumventing Defenses For Distributed Learning
- AllenNLP Interpret: Explaining Predictions of NLP Models
- Alleviating Label Switching with Optimal Transport
- Almost Horizon-Free Structure-Aware Best Policy Identification with a Generative Model
- A Mean Field Theory of Quantized Deep Networks: The Quantization-Depth Trade-Off
- A Meta-Analysis of Overfitting in Machine Learning
- A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning
- A Model to Search for Synthesizable Molecules
- Amortized Bethe Free Energy Minimization for Learning MRFs
- An Accelerated Decentralized Stochastic Proximal Algorithm for Finite Sums
- An Adaptive Empirical Bayesian Method for Sparse Deep Learning
- An adaptive Mirror-Prox method for variational inequalities with singular operators
- An adaptive nearest neighbor rule for classification
- An Algorithmic Framework For Differentially Private Data Analysis on Trusted Processors
- An Algorithm to Learn Polytree Networks with Hidden Nodes
- A Necessary and Sufficient Stability Notion for Adaptive Generalization
- An Embedding Framework for Consistent Polyhedral Surrogates
- A neurally plausible model for online recognition and postdiction in a dynamical environment
- A neurally plausible model learns successor representations in partially observable environments
- A New Defense Against Adversarial Images: Turning a Weakness into a Strength
- A New Distribution on the Simplex with Auto-Encoding Applications
- A New Perspective on Pool-Based Active Classification and False-Discovery Control
- An Improved Analysis of Training Over-parameterized Deep Neural Networks
- An Inexact Augmented Lagrangian Framework for Nonconvex Optimization with Nonlinear Constraints
- ANODEV2: A Coupled Neural ODE Framework
- A Nonconvex Approach for Exact and Efficient Multichannel Sparse Blind Deconvolution
- A Normative Theory for Causal Inference and Bayes Factor Computation in Neural Circuits
- Anti-efficient encoding in emergent communication
- A Polynomial Time Algorithm for Log-Concave Maximum Likelihood via Locally Exponential Families
- Approximate Bayesian Inference for a Mechanistic Model of Vesicle Release at a Ribbon Synapse
- Approximate Feature Collisions in Neural Nets
- Approximate Inference Turns Deep Networks into Gaussian Processes
- Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systems
- Approximating the Permanent by Sampling from Adaptive Partitions
- Approximation Ratios of Graph Neural Networks for Combinatorial Problems
- A Primal Dual Formulation For Deep Learning With Constraints
- A Primal-Dual link between GANs and Autoencoders
- A Prior of a Googol Gaussians: a Tensor Ring Induced Prior for Generative Models
- Arbicon-Net: Arbitrary Continuous Geometric Transformation Networks for Image Registration
- Are Anchor Points Really Indispensable in Label-Noise Learning?
- Are deep ResNets provably better than linear predictors?
- Are Disentangled Representations Helpful for Abstract Visual Reasoning?
- A Refined Margin Distribution Analysis for Forest Representation Learning
- A Regularized Approach to Sparse Optimal Policy in Reinforcement Learning
- Are Labels Required for Improving Adversarial Robustness?
- Are sample means in multi-armed bandits positively or negatively biased?
- Are Sixteen Heads Really Better than One?
- A Robust Non-Clairvoyant Dynamic Mechanism for Contextual Auctions
- A Self Validation Network for Object-Level Human Attention Estimation
- A Similarity-preserving Network Trained on Transformed Images Recapitulates Salient Features of the Fly Motion Detection Circuit
- A Simple Baseline for Bayesian Uncertainty in Deep Learning
- Ask not what AI can do, but what AI should do: Towards a framework of task delegability
- A Solvable High-Dimensional Model of GAN
- Assessing Disparate Impact of Personalized Interventions: Identifiability and Bounds
- Assessing Social and Intersectional Biases in Contextualized Word Representations
- A state-space model for inferring effective connectivity of latent neural dynamics from simultaneous EEG/fMRI
- A Step Toward Quantifying Independently Reproducible Machine Learning Research
- A Stochastic Composite Gradient Method with Incremental Variance Reduction
- A Structured Prediction Approach for Generalization in Cooperative Multi-Agent Reinforcement Learning
- Asymmetric Valleys: Beyond Sharp and Flat Local Minima
- Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein Distance
- Asymptotics for Sketching in Least Squares Regression
- A Tensorized Transformer for Language Modeling
- AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification
- Attentive State-Space Modeling of Disease Progression
- Attribution-Based Confidence Metric For Deep Neural Networks
- Augmented Neural ODEs
- A Unified Bellman Optimality Principle Combining Reward Maximization and Empowerment
- A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning
- A unified theory for the origin of grid cells through the lens of pattern formation
- A unified variance-reduced accelerated gradient method for convex optimization
- A Unifying Framework for Spectrum-Preserving Graph Sparsification and Coarsening
- A Universally Optimal Multistage Accelerated Stochastic Gradient Method
- AutoAssist: A Framework to Accelerate Training of Deep Neural Networks
- AutoPrune: Automatic Network Pruning by Regularizing Auxiliary Parameters
- Average-Case Averages: Private Algorithms for Smooth Sensitivity and Mean Estimation
- Average Case Column Subset Selection for Entrywise ℓ1-Norm Loss
- Average Individual Fairness: Algorithms, Generalization and Experiments
- A Zero-Positive Learning Approach for Diagnosing Software Performance Regressions
- Backpropagation-Friendly Eigendecomposition
- Backprop with Approximate Activations for Memory-efficient Network Training
- Balancing Efficiency and Fairness in On-Demand Ridesourcing
- Bandits with Feedback Graphs and Switching Costs
- Band-Limited Gaussian Processes: The Sinc Kernel
- BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning
- Batched Multi-armed Bandits Problem
- Bat-G net: Bat-inspired High-Resolution 3D Image Reconstruction using Ultrasonic Echoes
- Bayesian Batch Active Learning as Sparse Subset Approximation
- Bayesian Deep Learning
- Bayesian Joint Estimation of Multiple Graphical Models
- Bayesian Layers: A Module for Neural Network Uncertainty
- Bayesian Learning of Sum-Product Networks
- Bayesian Optimization under Heavy-tailed Payoffs
- Bayesian Optimization with Unknown Search Space
- Beating SGD Saturation with Tail-Averaging and Minibatching
- BehaveNet: nonlinear embedding and Bayesian neural decoding of behavioral videos
- Better Exploration with Optimistic Actor Critic
- Better Transfer Learning with Inferred Successor Maps
- Beyond Alternating Updates for Matrix Factorization with Inertial Bregman Proximal Gradient Algorithms
- Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPs
- Beyond first order methods in machine learning systems
- Beyond Online Balanced Descent: An Optimal Algorithm for Smoothed Online Optimization
- Beyond temperature scaling: Obtaining well-calibrated multi-class probabilities with Dirichlet calibration
- Beyond the Single Neuron Convex Barrier for Neural Network Certification
- Beyond Vector Spaces: Compact Data Representation as Differentiable Weighted Graphs
- Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting
- Biases for Emergent Communication in Multi-agent Reinforcement Learning
- BIM-GAN: a sketch to layout, 3D, and VR tool for architectural floor plan design
- Biological and Artificial Reinforcement Learning
- Bipartite expander Hopfield networks as self-decoding high-capacity error correcting codes
- BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling
- Blended Matching Pursuit
- Blind Super-Resolution Kernel Estimation using an Internal-GAN
- Block Coordinate Regularization by Denoising
- Blocking Bandits
- Blow: a single-scale hyperconditioned flow for non-parallel raw-audio voice conversion
- Bootstrapping Upper Confidence Bound
- Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs
- Breaking the Glass Ceiling for Embedding-Based Classifiers for Large Output Spaces
- Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks
- Bridging Game Theory and Deep Learning
- Bridging Machine Learning and Logical Reasoning by Abductive Learning
- Budgeted Reinforcement Learning in Continuous State Space
- Calculating Optimistic Likelihoods Using (Geodesically) Convex Optimization
- Calibration tests in multi-class classification: A unifying framework
- Can SGD Learn Recurrent Neural Networks with Provable Generalization?
- Can Unconditional Language Models Recover Arbitrary Sentences?
- Can you trust your model's uncertainty? Evaluating predictive uncertainty under dataset shift
- Capacity Bounded Differential Privacy
- Cascaded Dilated Dense Network with Two-step Data Consistency for MRI Reconstruction
- Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution
- Catastrophic Forgetting Meets Negative Transfer: Batch Spectral Shrinkage for Safe Transfer Learning
- Categorized Bandits
- Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation
- Causal Confusion in Imitation Learning
- Causal Regularization
- Censored Semi-Bandits: A Framework for Resource Allocation with Censored Feedback
- Certainty Equivalence is Efficient for Linear Quadratic Control
- Certifiable Robustness to Graph Perturbations
- Certified Adversarial Robustness with Additive Noise
- Certifying Geometric Robustness of Neural Networks
- Channel Gating Neural Networks
- Characterization and Learning of Causal Graphs with Latent Variables from Soft Interventions
- Characterizing Bias in Classifiers using Generative Models
- Characterizing the Exact Behaviors of Temporal Difference Learning Algorithms Using Markov Jump Linear System Theory
- Chasing Ghosts: Instruction Following as Bayesian State Tracking
- Chirality Nets for Human Pose Regression
- CiML 2019: Machine Learning Competitions for All
- Classification Accuracy Score for Conditional Generative Models
- Classification-by-Components: Probabilistic Modeling of Reasoning over a Set of Components
- CNN^{2}: Viewpoint Generalization via a Binocular Vision
- Coda: An End-to-End Neural Program Decompiler
- Code Generation as a Dual Task of Code Summarization
- Co-Generation with GANs using AIS based HMC
- Cold Case: The Lost MNIST Digits
- Combinatorial Bandits with Relative Feedback
- Combinatorial Bayesian Optimization using the Graph Cartesian Product
- Combinatorial Inference against Label Noise
- Combining Generative and Discriminative Models for Hybrid Inference
- Communication-Efficient Distributed Blockwise Momentum SGD with Error-Feedback
- Communication-Efficient Distributed Learning via Lazily Aggregated Quantized Gradients
- Communication-efficient Distributed SGD with Sketching
- Communication trade-offs for Local-SGD with large step size
- Compacting, Picking and Growing for Unforgetting Continual Learning
- Comparing distributions: ℓ1 geometry improves kernel two-sample testing
- Comparing Unsupervised Word Translation Methods Step by Step
- Comparison Against Task Driven Artificial Neural Networks Reveals Functional Organization of Mouse Visual Cortex
- Competition Track Day 1
- Competition Track Day 2
- Competitive Gradient Descent
- Compiler Auto-Vectorization with Imitation Learning
- Complexity of Highly Parallel Non-Smooth Convex Optimization
- Compositional De-Attention Networks
- Compositional generalization through meta sequence-to-sequence learning
- Compositional Plan Vectors
- Compression with Flows via Local Bits-Back Coding
- Computational Mirrors: Blind Inverse Light Transport by Deep Matrix Factorization
- Computational Separations between Sampling and Optimization
- Computing Full Conformal Prediction Set with Approximate Homotopy
- Computing Linear Restrictions of Neural Networks
- Concentration of risk measures: A Wasserstein distance approach
- CondConv: Conditionally Parameterized Convolutions for Efficient Inference
- Conditional Independence Testing using Generative Adversarial Networks
- Conditional Structure Generation through Graph Variational Generative Adversarial Nets
- Conformalized Quantile Regression
- Conformal Prediction Under Covariate Shift
- Connections Between Mirror Descent, Thompson Sampling and the Information Ratio
- Connective Cognition Network for Directional Visual Commonsense Reasoning
- Consistency-based Semi-supervised Learning for Object detection
- Constrained deep neural network architecture search for IoT devices accounting for hardware calibration
- Constrained Reinforcement Learning Has Zero Duality Gap
- Constraint-based Causal Structure Learning with Consistent Separating Sets
- Context and Compositionality in Biological and Artificial Neural Systems
- Contextual Bandits with Cross-Learning
- Continual Unsupervised Representation Learning
- Continuous Hierarchical Representations with Poincaré Variational Auto-Encoders
- Continuous-time Models for Stochastic Optimization Algorithms
- Control Batch Size and Learning Rate to Generalize Well: Theoretical and Empirical Evidence
- Controllable Text-to-Image Generation
- Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representation
- Controlling Neural Level Sets
- Control What You Can: Intrinsically Motivated Task-Planning Agent
- Convergence Guarantees for Adaptive Bayesian Quadrature Methods
- Convergence of Adversarial Training in Overparametrized Neural Networks
- Convergence-Rate-Matching Discretization of Accelerated Optimization Flows Through Opportunistic State-Triggered Control
- Convergent Policy Optimization for Safe Reinforcement Learning
- Convolution with even-sized kernels and symmetric padding
- Coordinated hippocampal-entorhinal replay as structural inference
- Copula-like Variational Inference
- Copula Multi-label Learning
- Copulas as High-Dimensional Generative Models: Vine Copula Autoencoders
- Coresets for Archetypal Analysis
- Coresets for Clustering with Fairness Constraints
- Cormorant: Covariant Molecular Neural Networks
- Correlated Uncertainty for Learning Dense Correspondences from Noisy Labels
- Correlation Clustering with Adaptive Similarity Queries
- Correlation clustering with local objectives
- Correlation in Extensive-Form Games: Saddle-Point Formulation and Benchmarks
- Correlation Priors for Reinforcement Learning
- Cost Effective Active Search
- Counting the Optimal Solutions in Graphical Models
- Covariate-Powered Empirical Bayes Estimation
- CPM-Nets: Cross Partial Multi-View Networks
- Cross Attention Network for Few-shot Classification
- Cross-channel Communication Networks
- Cross-Domain Transferability of Adversarial Perturbations
- Cross-lingual Language Model Pretraining
- Cross-Modal Learning with Adversarial Samples
- Cross-sectional Learning of Extremal Dependence among Financial Assets
- Crowdsourcing via Pairwise Co-occurrences: Identifiability and Algorithms
- Curriculum-guided Hindsight Experience Replay
- Curvilinear Distance Metric Learning
- CXPlain: Causal Explanations for Model Interpretation under Uncertainty
- DAC: The Double Actor-Critic Architecture for Learning Options
- Dancing to Music
- Data Cleansing for Models Trained with SGD
- Data-Dependence of Plateau Phenomenon in Learning with Neural Network --- Statistical Mechanical Analysis
- Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation
- DATA: Differentiable ArchiTecture Approximation
- Data-driven Estimation of Sinusoid Frequencies
- Data Parameters: A New Family of Parameters for Learning a Differentiable Curriculum
- Debiased Bayesian inference for average treatment effects
- Decentralized Cooperative Stochastic Bandits
- Decentralized sketching of low rank matrices
- Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask
- Deep Active Learning with a Neural Architecture Search
- Deep Equilibrium Models
- Deep Gamblers: Learning to Abstain with Portfolio Theory
- Deep Generalized Method of Moments for Instrumental Variable Analysis
- Deep Generative Video Compression
- Deep imitation learning for molecular inverse problems
- Deep Leakage from Gradients
- Deep Learning with Bayesian Principles
- Deep Learning without Weight Transport
- Deep Model Transferability from Attribution Maps
- Deep Multimodal Multilinear Fusion with High-order Polynomial Pooling
- Deep Multi-State Dynamic Recurrent Neural Networks Operating on Wavelet Based Neural Features for Robust Brain Machine Interfaces
- Deep Random Splines for Point Process Intensity Estimation of Neural Population Data
- Deep Reinforcement Learning
- Deep ReLU Networks Have Surprisingly Few Activation Patterns
- Deep RGB-D Canonical Correlation Analysis For Sparse Depth Completion
- Deep Scale-spaces: Equivariance Over Scale
- Deep Set Prediction Networks
- Deep Signature Transforms
- Deep Space-Time Prior for Realtime Mobile Novel View Synthesis
- Deep Structured Prediction for Facial Landmark Detection
- Deep Supervised Summarization: Algorithm and Application to Learning Instructions
- DeepUSPS: Deep Robust Unsupervised Saliency Prediction via Self-supervision
- DeepWave: A Recurrent Neural-Network for Real-Time Acoustic Imaging
- Defending Against Neural Fake News
- Defending Neural Backdoors via Generative Distribution Modeling
- Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training
- Deliberative Explanations: visualizing network insecurities
- Demystifying Black-box Models with Symbolic Metamodels
- Depth-First Proof-Number Search with Heuristic Edge Cost and Application to Chemical Synthesis Planning
- Detecting Overfitting via Adversarial Examples
- DetNAS: Backbone Search for Object Detection
- DETOX: A Redundancy-based Framework for Faster and More Robust Gradient Aggregation
- Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks
- DFNets: Spectral CNNs for Graphs with Feedback-Looped Filters
- Dichotomize and Generalize: PAC-Bayesian Binary Activated Deep Neural Networks
- Diffeomorphic Temporal Alignment Nets
- Differentiable Cloth Simulation for Inverse Problems
- Differentiable Convex Optimization Layers
- Differentiable Ranking and Sorting using Optimal Transport
- Differentially Private Algorithms for Learning Mixtures of Separated Gaussians
- Differentially Private Anonymized Histograms
- Differentially Private Bagging: Improved utility and cheaper privacy than subsample-and-aggregate
- Differentially Private Bayesian Linear Regression
- Differentially Private Covariance Estimation
- Differentially Private Distributed Data Summarization under Covariate Shift
- Differentially Private Markov Chain Monte Carlo
- Differential Privacy Has Disparate Impact on Model Accuracy
- Diffusion Improves Graph Learning
- Dimensionality reduction: theoretical perspective on practical measures
- Dimension-Free Bounds for Low-Precision Training
- DINGO: Distributed Newton-Type Method for Gradient-Norm Optimization
- Direct Estimation of Differential Functional Graphical Models
- Direct Optimization through argmax for Discrete Variational Auto-Encoder
- Discovering Neural Wirings
- Discovering Neural Wirings Neural Network Visualizer
- Discovery of Useful Questions as Auxiliary Tasks
- Discrete Flows: Invertible Generative Models of Discrete Data
- Discrete Object Generation with Reversible Inductive Construction
- Discrimination in Online Markets: Effects of Social Bias on Learning from Reviews and Policy Design
- Discriminative Topic Modeling with Logistic LDA
- Discriminator optimal transport
- Disentangled behavioural representations
- Disentangling Influence: Using disentangled representations to audit model predictions
- DiskANN: Fast Accurate Billion-point Nearest Neighbor Search on a Single Node
- DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction
- Distinguishing Distributions When Samples Are Strategically Transformed
- Distributed estimation of the inverse Hessian by determinantal averaging
- Distributed Low-rank Matrix Factorization With Exact Consensus
- Distributionally Robust Optimization and Generalization in Kernel Methods
- Distributional Policy Optimization: An Alternative Approach for Continuous Control
- Distributional Reward Decomposition for Reinforcement Learning
- Distribution-Independent PAC Learning of Halfspaces with Massart Noise
- Distribution Learning of a Random Spatial Field with a Location-Unaware Mobile Sensor
- Distribution oblivious, risk-aware algorithms for multi-armed bandits with unbounded rewards
- Divergence-Augmented Policy Optimization
- Divide and Couple: Using Monte Carlo Variational Objectives for Posterior Approximation
- DM2C: Deep Mixed-Modal Clustering
- Document Intelligence
- Domain Generalization via Model-Agnostic Learning of Semantic Features
- Domes to Drones: Self-Supervised Active Triangulation for 3D Human Pose Reconstruction
- Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapse
- Don't take it lightly: Phasing optical random projections with unknown operators
- “Do the right thing”: machine learning and causal inference for improved decision making
- Double Quantization for Communication-Efficient Distributed Optimization
- Doubly-Robust Lasso Bandit
- DppNet: Approximating Determinantal Point Processes with Deep Networks
- Drill-down: Interactive Retrieval of Complex Scenes using Natural Language Queries
- DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs
- DTWNet: a Dynamic Time Warping Network
- Dual Adversarial Semantics-Consistent Network for Generalized Zero-Shot Learning
- DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections
- Dual Variational Generation for Low Shot Heterogeneous Face Recognition
- D-VAE: A Variational Autoencoder for Directed Acyclic Graphs
- Dying Experts: Efficient Algorithms with Optimal Regret Bounds
- Dynamic Ensemble Modeling Approach to Nonstationary Neural Decoding in Brain-Computer Interfaces
- Dynamic Incentive-Aware Learning: Robust Pricing in Contextual Auctions
- Dynamic Local Regret for Non-convex Online Forecasting
- Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup
- E2-Train: Training State-of-the-art CNNs with Over 80% Less Energy
- Ease-of-Teaching and Language Structure from Emergent Communication
- Effective End-to-end Unsupervised Outlier Detection via Inlier Priority of Discriminative Network
- Efficient Algorithms for Smooth Minimax Optimization
- Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks
- Efficient and Thrifty Voting by Any Means Necessary
- Efficient Approximation of Deep ReLU Networks for Functions on Low Dimensional Manifolds
- Efficient characterization of electrically evoked responses for neural interfaces
- Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control
- Efficient Convex Relaxations for Streaming PCA
- Efficient Deep Approximation of GMMs
- Efficient Forward Architecture Search
- Efficient Graph Generation with Graph Recurrent Attention Networks
- Efficient Identification in Linear Structural Causal Models with Instrumental Cutsets
- Efficiently avoiding saddle points with zero order methods: No gradients required
- Efficiently escaping saddle points on manifolds
- Efficiently Estimating Erdos-Renyi Graphs with Node Differential Privacy
- Efficiently Learning Fourier Sparse Set Functions
- Efficient Meta Learning via Minibatch Proximal Update
- Efficient Near-Optimal Testing of Community Changes in Balanced Stochastic Block Models
- Efficient Neural Architecture Transformation Search in Channel-Level for Object Detection
- Efficient online learning with kernels for adversarial large scale problems
- Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model
- Efficient Processing of Deep Neural Network: from Algorithms to Hardware Architectures
- Efficient Pure Exploration in Adaptive Round Model
- Efficient Regret Minimization Algorithm for Extensive-Form Correlated Equilibrium
- Efficient Rematerialization for Deep Networks
- Efficient Smooth Non-Convex Stochastic Compositional Optimization via Stochastic Recursive Gradient Descent
- Efficient Symmetric Norm Regression via Linear Sketching
- Einconv: Exploring Unexplored Tensor Network Decompositions for Convolutional Neural Networks
- Elliptical Perturbations for Differential Privacy
- Embedding Symbolic Knowledge into Deep Networks
- EMC2: Energy Efficient Machine Learning and Cognitive Computing (5th edition)
- Emergence of Object Segmentation in Perturbed Generative Models
- Emergent Communication: Towards Natural Language
- Empathy based Affective Portrait Painter
- Empirically Measuring Concentration: Fundamental Limits on Intrinsic Robustness
- Enabling hyperparameter optimization in sequential autoencoders for spiking neural data
- End to end learning and optimization on graphs
- End-to-End Learning on 3D Protein Structure for Interface Prediction
- Energy-Inspired Models: Learning with Sampler-Induced Distributions
- Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting
- Envy-Free Classification
- Episodic Memory in Lifelong Language Learning
- Epsilon-Best-Arm Identification in Pay-Per-Reward Multi-Armed Bandits
- Equal Opportunity in Online Classification with Partial Feedback
- Equipping Experts/Bandits with Long-term Memory
- Equitable Stable Matchings in Quadratic Time
- Error Correcting Output Codes Improve Probability Estimation and Adversarial Robustness of Deep Neural Networks
- Escaping from saddle points on Riemannian manifolds
- Estimating Convergence of Markov chains with L-Lag Couplings
- Estimating Entropy of Distributions in Constant Space
- ETNet: Error Transition Network for Arbitrary Style Transfer
- Evaluating Protein Transfer Learning with TAPE
- Exact Combinatorial Optimization with Graph Convolutional Neural Networks
- Exact Gaussian Processes on a Million Data Points
- Exact inference in structured prediction
- Exact Rate-Distortion in Autoencoders via Echo Noise
- Exact sampling of determinantal point processes with sublinear time preprocessing
- exBERT: A Visual Analysis Tool to Explain BERT's Learned Representations
- Experience Replay for Continual Learning
- Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets
- Explanations can be manipulated and geometry is to blame
- Explicit Disentanglement of Appearance and Perspective in Generative Models
- Explicit Explore-Exploit Algorithms in Continuous State Spaces
- Explicitly disentangling image content from translation and rotation with spatial-VAE
- Explicit Planning for Efficient Exploration in Reinforcement Learning
- Exploiting Local and Global Structure for Point Cloud Semantic Segmentation with Contextual Point Representations
- Exploration Bonus for Regret Minimization in Discrete and Continuous Average Reward MDPs
- Exploration via Hindsight Goal Generation
- Exploring Algorithmic Fairness in Robust Graph Covering Problems
- Exponential Family Estimation via Adversarial Dynamics Embedding
- Exponentially convergent stochastic k-PCA without variance reduction
- Expressive power of tensor-network factorizations for probabilistic modeling
- Extending Stein's unbiased risk estimator to train deep denoisers with correlated pairs of noisy images
- Extreme Classification in Log Memory using Count-Min Sketch: A Case Study of Amazon Search with 50M Products
- F1/10: An open-source 1/10th scale platform for autonomous racing and reinforcement learning
- Face Reconstruction from Voice using Generative Adversarial Networks
- Facility Location Problem in Differential Privacy Model Revisited
- Factor Group-Sparse Regularization for Efficient Low-Rank Matrix Recovery
- Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift
- Fair Algorithms for Clustering
- Fair ML in Healthcare
- Fast and Accurate Least-Mean-Squares Solvers
- Fast and Accurate Stochastic Gradient Estimation
- Fast and Flexible Multi-Task Classification using Conditional Neural Adaptive Processes
- Fast and Furious Learning in Zero-Sum Games: Vanishing Regret with Non-Vanishing Step Sizes
- Fast and Provable ADMM for Learning with Generative Priors
- Fast AutoAugment
- Fast Convergence of Belief Propagation to Global Optima: Beyond Correlation Decay
- Fast Convergence of Natural Gradient Descent for Over-Parameterized Neural Networks
- Fast Decomposable Submodular Function Minimization using Constrained Total Variation
- Fast Efficient Hyperparameter Tuning for Policy Gradient Methods
- Faster Boosting with Smaller Memory
- Faster width-dependent algorithm for mixed packing and covering LPs
- Fast Low-rank Metric Learning for Large-scale and High-dimensional Data
- Fast Parallel Algorithms for Statistical Subset Selection Problems
- Fast, Provably convergent IRLS Algorithm for p-norm Linear Regression
- Fast-rate PAC-Bayes Generalization Bounds via Shifted Rademacher Processes
- Fast Sparse Group Lasso
- FastSpeech: Fast, Robust and Controllable Text to Speech
- Fast Structured Decoding for Sequence Models
- Fast structure learning with modular regularization
- Few-shot Video-to-Video Synthesis
- Finding Friend and Foe in Multi-Agent Games
- Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias
- Fine-grained Optimization of Deep Neural Networks
- Finite-Sample Analysis for SARSA with Linear Function Approximation
- Finite-time Analysis of Approximate Policy Iteration for the Linear Quadratic Regulator
- Finite-Time Performance Bounds and Adaptive Learning Rate Selection for Two Time-Scale Reinforcement Learning
- First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise
- First order expansion of convex regularized estimators
- First-order methods almost always avoid saddle points: The case of vanishing step-sizes
- First Order Motion Model for Image Animation
- Fisher Efficient Inference of Intractable Models
- Fixing Implicit Derivatives: Trust-Region Based Learning of Continuous Energy Functions
- Fixing the train-test resolution discrepancy
- Flattening a Hierarchical Clustering through Active Learning
- Flexible information routing in neural populations through stochastic comodulation
- Flexible Modeling of Diversity with Strongly Log-Concave Distributions
- Flow-based Image-to-Image Translation with Feature Disentanglement
- Focused Quantization for Sparse CNNs
- Fooling Neural Network Interpretations via Adversarial Model Manipulation
- Foundations of Comparison-Based Hierarchical Clustering
- FreeAnchor: Learning to Match Anchors for Visual Object Detection
- From Complexity to Simplicity: Adaptive ES-Active Subspaces for Blackbox Optimization
- From deep learning to mechanistic understanding in neuroscience: the structure of retinal prediction
- From System 1 Deep Learning to System 2 Deep Learning
- From voxels to pixels and back: Self-supervision in natural-image reconstruction from fMRI
- Full-Gradient Representation for Neural Network Visualization
- Fully Dynamic Consistent Facility Location
- Fully Neural Network based Model for General Temporal Point Processes
- Fully Parameterized Quantile Function for Distributional Reinforcement Learning
- Functional Adversarial Attacks
- Function-Space Distributions over Kernels
- G2SAT: Learning to Generate SAT Formulas
- Game Design for Eliciting Distinguishable Behavior
- Gated CRF Loss for Weakly Supervised Semantic Image Segmentation
- Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks
- Gaussian-Based Pooling for Convolutional Neural Networks
- General E(2)-Equivariant Steerable CNNs
- Generalization Bounds for Neural Networks via Approximate Description Length
- Generalization Bounds in the Predict-then-Optimize Framework
- Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks
- Generalization Error Analysis of Quantized Compressive Learning
- Generalization in Generative Adversarial Networks: A Novel Perspective from Privacy Protection
- Generalization in multitask deep neural classifiers: a statistical physics approach
- Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck
- Generalization of Reinforcement Learners with Working and Episodic Memory
- Generalized Block-Diagonal Structure Pursuit: Learning Soft Latent Task Assignment against Negative Transfer
- Generalized Matrix Means for Semi-Supervised Learning with Multilayer Graphs
- Generalized Off-Policy Actor-Critic
- Generalized Sliced Wasserstein Distances
- General Proximal Incremental Aggregated Gradient Algorithms: Better and Novel Results under General Scheme
- Generating Diverse High-Fidelity Images with VQ-VAE-2
- Generative Modeling by Estimating Gradients of the Data Distribution
- Generative Models for Graph-Based Protein Design
- Generative Well-intentioned Networks
- GENO -- GENeric Optimization for Classical Machine Learning
- GENO -- Optimization for Classical Machine Learning Made Fast and Easy
- Geometry-Aware Neural Rendering
- GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs
- Global Convergence of Gradient Descent for Deep Linear Residual Networks
- Global Convergence of Least Squares EM for Demixing Two Log-Concave Densities
- Global Guarantees for Blind Demodulation with Generative Priors
- Globally Convergent Newton Methods for Ill-conditioned Generalized Self-concordant Losses
- Globally Optimal Learning for Structured Elliptical Losses
- Globally optimal score-based learning of directed acyclic graphs in high-dimensions
- Global Sparse Momentum SGD for Pruning Very Deep Neural Networks
- Glyce: Glyph-vectors for Chinese Character Representations
- GNNExplainer: Generating Explanations for Graph Neural Networks
- Goal-conditioned Imitation Learning
- Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning
- GOT: An Optimal Transport framework for Graph comparison
- GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism
- Gradient-based Adaptive Markov Chain Monte Carlo
- Gradient based sample selection for online continual learning
- Gradient Dynamics of Shallow Univariate ReLU Networks
- Gradient Information for Representation and Modeling
- Graph Agreement Models for Semi-Supervised Learning
- Graph-based Discriminators: Sample Complexity and Expressiveness
- Graph-Based Semi-Supervised Learning with Non-ignorable Non-response
- Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels
- Graph Normalizing Flows
- Graph Representation Learning
- Graph Structured Prediction Energy Networks
- Graph Transformer Networks
- Greedy Sampling for Approximate Clustering in the Presence of Outliers
- Grid Saliency for Context Explanations of Semantic Segmentation
- Group Retention when Using Machine Learning in Sequential Decision Making: the Interplay between User Dynamics and Fairness
- GRU-ODE-Bayes: Continuous Modeling of Sporadically-Observed Time Series
- Guided Meta-Policy Search
- Guided Similarity Separation for Image Retrieval
- Hamiltonian descent for composite objectives
- Hamiltonian Neural Networks
- Handling correlated and repeated measurements with the smoothed multivariate square-root Lasso
- Heterogeneous Graph Learning for Visual Commonsense Reasoning
- Hierarchical Decision Making by Generating and Following Natural Language Instructions
- Hierarchical Optimal Transport for Document Representation
- Hierarchical Optimal Transport for Multimodal Distribution Alignment
- Hierarchical Reinforcement Learning with Advantage-Based Auxiliary Rewards
- High-dimensional multivariate forecasting with low-rank Gaussian Copula Processes
- High-Dimensional Optimization in Adaptive Random Subspaces
- High Fidelity Video Prediction with Large Stochastic Recurrent Neural Networks
- High-Quality Self-Supervised Deep Image Denoising
- Hindsight Credit Assignment
- "How can this Paper get in?" - A game to advise researchers when writing for a top AI conference
- How degenerate is the parametrization of neural networks with the ReLU activation function?
- How to Initialize your Network? Robust Initialization for WeightNorm & ResNets
- How to Know
- Human Behavior Modeling with Machine Learning: Opportunities and Challenges
- Human Gesture Recognition using Spiking Input on Akida Neuromorphic Platform
- Hybrid 8-bit Floating Point (HFP8) Training and Inference for Deep Neural Networks
- HYPE: A Benchmark for Human eYe Perceptual Evaluation of Generative Models
- Hyperbolic Graph Convolutional Neural Networks
- Hyperbolic Graph Neural Networks
- HyperGCN: A New Method For Training Graph Convolutional Networks on Hypergraphs
- Hyper-Graph-Network Decoders for Block Codes
- Hyperparameter Learning via Distributional Transfer
- Hyperspherical Prototype Networks
- Hypothesis Set Stability and Generalization
- Icebreaker: Element-wise Efficient Information Acquisition with a Bayesian Deep Latent Gaussian Model
- Identification of Conditional Causal Effects under Markov Equivalence
- Identifying Causal Effects via Context-specific Independence Relations
- Image Captioning: Transforming Objects into Words
- Image Synthesis with a Single (Robust) Classifier
- Imitation Learning and its Application to Natural Language Generation
- Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement
- Imitation-Projected Programmatic Reinforcement Learning
- Immersions - How Does Music Sound to Artificial Ears?
- Implicit Generation and Modeling with Energy Based Models
- Implicitly learning to reason in first-order logic
- Implicit Posterior Variational Inference for Deep Gaussian Processes
- Implicit Regularization for Optimal Sparse Recovery
- Implicit Regularization in Deep Matrix Factorization
- Implicit Regularization of Accelerated Methods in Hilbert Spaces
- Implicit Regularization of Discrete Gradient Dynamics in Linear Neural Networks
- Implicit Semantic Data Augmentation for Deep Networks
- Importance Resampling for Off-policy Prediction
- Importance Weighted Hierarchical Variational Inference
- Improved Precision and Recall Metric for Assessing Generative Models
- Improved Regret Bounds for Bandit Combinatorial Optimization
- Improving Black-box Adversarial Attacks with a Transfer-based Prior
- Improving Textual Network Learning with Variational Homophilic Embeddings
- Incremental Few-Shot Learning with Attention Attractor Networks
- Incremental Scene Synthesis
- Individual Regret in Cooperative Nonstochastic Multi-Armed Bandits
- Inducing brain-relevant bias in natural language processing models
- Information Competing Process for Learning Diversified Representations
- Information-Theoretic Confidence Bounds for Reinforcement Learning
- Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates
- Information Theory and Machine Learning
- Infra-slow brain dynamics as a marker for cognitive function and decline
- Inherent Tradeoffs in Learning Fair Representations
- Inherent Weight Normalization in Stochastic Neural Networks
- Initialization of ReLUs for Dynamical Isometry
- In-Place Zero-Space Memory Protection for CNN
- Input-Cell Attention Reduces Vanishing Saliency of Recurrent Neural Networks
- Input-Output Equivalence of Unitary and Contractive RNNs
- Input Similarity from the Neural Network Perspective
- Integer Discrete Flows and Lossless Compression
- Integrating Bayesian and Discriminative Sparse Kernel Machines for Multi-class Active Learning
- Integrating Markov processes with structural causal modeling enables counterfactual inference in complex systems
- Interaction Hard Thresholding: Consistent Sparse Quadratic Regression in Sub-quadratic Time and Space
- Interior-Point Methods Strike Back: Solving the Wasserstein Barycenter Problem
- Interlaced Greedy Algorithm for Maximization of Submodular Functions in Nearly Linear Time
- Interpretable Comparison of Distributions and Models
- Interpreting and improving natural-language processing (in machines) with natural language-processing (in the brain)
- Interval timing in deep reinforcement learning agents
- Intrinsically Efficient, Stable, and Bounded Off-Policy Evaluation for Reinforcement Learning
- Intrinsic dimension of data representations in deep neural networks
- Invariance and identifiability issues for word embeddings
- Invariance-inducing regularization using worst-case transformations suffices to boost accuracy and spatial robustness
- Invertible Convolutional Flow
- Inverting Deep Generative models, One layer at a time
- Invert to Learn to Invert
- Is Deeper Better only when Shallow is Good?
- iSplit LBI: Individualized Partial Ranking with Ties via Split LBI
- Iterative Least Trimmed Squares for Mixed Linear Regression
- Joint Optimization of Tree-based Index and Deep Model for Recommender Systems
- Joint-task Self-supervised Learning for Temporal Correspondence
- Joint Workshop on AI for Social Good
- Kalman Filter, Sensor Fusion, and Constrained Regression: Equivalences and Insights
- Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing Shaped Rewards
- KerGM: Kernelized Graph Matching
- Kernel-Based Approaches for Sequence Modeling: Connections to Neural Methods
- Kernel Instrumental Variable Regression
- Kernelized Bayesian Softmax for Text Generation
- Kernel quadrature with DPPs
- Kernel Stein Tests for Multiple Model Comparison
- Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration
- k-Means Clustering of Lines for Big Data
- KNG: The K-Norm Gradient Mechanism
- Knowledge Extraction with No Observable Data
- KR2ML - Knowledge Representation and Reasoning Meets Machine Learning
- Landmark Ordinal Embedding
- Language as an Abstraction for Hierarchical Deep Reinforcement Learning
- Large Memory Layers with Product Keys
- Large Scale Adversarial Representation Learning
- Large Scale Markov Decision Processes with Changing Rewards
- Large-scale optimal transport map estimation using projection pursuit
- Large Scale Structure of Neural Network Loss Landscapes
- Latent distance estimation for random geometric graphs
- Latent Ordinary Differential Equations for Irregularly-Sampled Time Series
- Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization
- Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks
- LCA: Loss Change Allocation for Neural Network Training
- L_DMI: A Novel Information-theoretic Loss Function for Training Deep Nets Robust to Label Noise
- Leader Stochastic Gradient Descent for Distributed Training of Deep Learning Models
- Learnable Tree Filter for Structure-preserving Feature Transform
- Learner-aware Teaching: Inverse Reinforcement Learning with Preferences and Constraints
- Learn, Imagine and Create: Text-to-Image Generation from Prior Knowledge
- Learning about an exponential amount of conditional distributions
- Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers
- Learning Auctions with Robust Incentive Guarantees
- Learning-Based Low-Rank Approximations
- Learning Bayesian Networks with Low Rank Conditional Probability Tables
- Learning by Abstraction: The Neural State Machine
- Learning Compositional Neural Programs with Recursive Tree Search and Planning
- Learning Conditional Deformable Templates with Convolutional Networks
- Learning Data Manipulation for Augmentation and Weighting
- Learning Deep Bilinear Transformation for Fine-grained Image Representation
- Learning Deterministic Weighted Automata with Queries and Counterexamples
- Learning Disentangled Representation for Robust Person Re-identification
- Learning Disentangled Representations for Recommendation
- Learning Distributions Generated by One-Layer ReLU Networks
- Learning dynamic polynomial proofs
- Learning Dynamics of Attention: Human Prior for Interpretable Machine Reasoning
- Learning elementary structures for 3D shape generation and matching
- Learning Erdos-Renyi Random Graphs via Edge Detecting Queries
- Learning Fairness in Multi-Agent Systems
- Learning from Bad Data via Generation
- Learning from brains how to regularize machines
- Learning from Label Proportions with Generative Adversarial Networks
- Learning from Trajectories via Subgoal Discovery
- Learning GANs and Ensembles Using Discrepancy
- Learning Generalizable Device Placement Algorithms for Distributed Machine Learning
- Learning Hawkes Processes from a handful of events
- Learning Hierarchical Priors in VAEs
- Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
- Learning in Generalized Linear Contextual Bandits with Stochastic Delays
- Learning-In-The-Loop Optimization: End-To-End Control And Co-Design Of Soft Robots Through Learned Deep Latent Representations
- Learning Latent Process from High-Dimensional Event Sequences via Efficient Sampling
- Learning Local Search Heuristics for Boolean Satisfiability
- Learning low-dimensional state embeddings and metastable clusters from time series data
- Learning Machines can Curl - Adaptive Deep Reinforcement Learning enables the robot Curly to win against human players in an icy world
- Learning Macroscopic Brain Connectomes via Group-Sparse Factorization
- Learning Mean-Field Games
- Learning Meaningful Representations of Life
- Learning metrics for persistence-based summaries and applications for graph classification
- Learning Mixtures of Plackett-Luce Models from Structured Partial Orders
- Learning Multiple Markov Chains via Adaptive Allocation
- Learning Nearest Neighbor Graphs from Noisy Distance Samples
- Learning Neural Networks with Adaptive Regularization
- Learning New Tricks From Old Dogs: Multi-Source Transfer Learning From Pre-Trained Networks
- Learning Non-Convergent Non-Persistent Short-Run MCMC Toward Energy-Based Model
- Learning nonlinear level sets for dimensionality reduction in function approximation
- Learning Nonsymmetric Determinantal Point Processes
- Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds
- Learning Perceptual Inference by Contrasting
- Learning Positive Functions with Pseudo Mirror Descent
- Learning Representations by Maximizing Mutual Information Across Views
- Learning Representations for Time Series Clustering
- Learning Reward Machines for Partially Observable Reinforcement Learning
- Learning Robust Global Representations by Penalizing Local Predictive Power
- Learning Robust Options by Conditional Value at Risk Optimization
- Learning Sample-Specific Models with Low-Rank Personalized Regression
- Learning search spaces for Bayesian optimization: Another view of hyperparameter transfer learning
- Learning Sparse Distributions using Iterative Hard Thresholding
- Learning Stable Deep Dynamics Models
- Learning step sizes for unfolded sparse coding
- Learning Temporal Pose Estimation from Sparsely-Labeled Videos
- Learning to Confuse: Generating Training Time Adversarial Data with Auto-Encoder
- Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity
- Learning to Correlate in Multi-Player General-Sum Sequential Games
- Learning to Infer Implicit Surfaces without 3D Supervision
- Learning to Learn By Self-Critique
- Learning to Optimize in Swarms
- Learning to Perform Local Rewriting for Combinatorial Optimization
- Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer
- Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis
- Learning to Predict Without Looking Ahead: World Models Without Forward Prediction
- Learning to Propagate for Graph Meta-Learning
- Learning to Screen
- Learning to Self-Train for Semi-Supervised Few-Shot Classification
- Learning Transferable Graph Exploration
- Learning Transferable Skills
- Learning with Rich Experience: Integration of Learning Paradigms
- Learning with Temporal Point Processes
- Legendre Memory Units: Continuous-Time Representation in Recurrent Neural Networks
- Levenshtein Transformer
- Leveraging Labeled and Unlabeled Data for Consistent Fair Binary Classification
- LIIR: Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning
- Likelihood-Free Overcomplete ICA and Applications In Causal Discovery
- Likelihood Ratios for Out-of-Distribution Detection
- Limitations of Lazy Training of Two-layers Neural Network
- Limitations of the empirical Fisher approximation for natural gradient descent
- Limiting Extrapolation in Linear Approximate Value Iteration
- Limits of Private Learning with Access to Public Data
- Linear Stochastic Bandits Under Safety Constraints
- List-decodable Linear Regression
- LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition
- Loaded DiCE: Trading off Bias and Variance in Any-Order Score Function Gradient Estimators for Reinforcement Learning
- Locality-Sensitive Hashing for f-Divergences: Mutual Information Loss and Beyond
- Localized Structured Prediction
- Locally Private Gaussian Estimation
- Locally Private Learning without Interaction Requires Separation
- Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronization
- Logarithmic Regret for Online Control
- Lookahead Optimizer: k steps forward, 1 step back
- Low-Complexity Nonparametric Bayesian Online Prediction with Universal Guarantees
- Lower Bounds on Adversarial Robustness from Optimal Transport
- Low-Rank Bandit Methods for High-Dimensional Dynamic Pricing
- Machine Learning and the Physical Sciences
- Machine Learning Estimation of Heterogeneous Treatment Effects with Instruments
- Machine Learning for Autonomous Driving
- Machine Learning for Computational Biology and Health
- Machine Learning for Health (ML4H): What makes machine learning in medicine different?
- Machine Learning for the Developing World (ML4D): Challenges and Risks
- Machine Learning Meets Single-Cell Biology: Insights and Challenges
- Machine Learning with Guarantees
- Machine Teaching of Active Sequential Learners
- MaCow: Masked Convolutional Generative Flow
- Making AI Forget You: Data Deletion in Machine Learning
- Making the Cut: A Bandit-based Approach to Tiered Interviewing
- Manifold denoising by Nonlinear Robust Principal Component Analysis
- Manifold-regression to predict from MEG/EEG brain signals without source modeling
- Manipulating a Learning Defender and Ways to Counteract
- Mapping Emotions: Discovering Structure in Mesoscale Electrical Brain Recordings
- Mapping State Space using Landmarks for Universal Goal Reaching
- Margin-Based Generalization Lower Bounds for Boosted Classifiers
- MarginGAN: Adversarial Training in Semi-Supervised Learning
- Markov Random Fields for Collaborative Filtering
- Massively scalable Sinkhorn distances via the Nyström method
- MAVEN: Multi-Agent Variational Exploration
- MaxGap Bandit: Adaptive Algorithms for Approximate Ranking
- Maximum Entropy Monte-Carlo Planning
- Maximum Expected Hitting Cost of a Markov Decision Process and Informativeness of Rewards
- Maximum Mean Discrepancy Gradient Flow
- Max-value Entropy Search for Multi-Objective Bayesian Optimization
- McDiarmid-Type Inequalities for Graph-Dependent Variables and Stability Bounds
- MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies
- Medical Imaging meets NeurIPS
- MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
- Melody Slot Machine
- Memory Efficient Adaptive Optimization
- Memory-oriented Decoder for Light Field Salient Object Detection
- Meta Architecture Search
- Meta-Curvature
- MetaInit: Initializing learning by learning to initialize
- Meta-Inverse Reinforcement Learning with Probabilistic Context Variables
- Metalearned Neural Memory
- Meta-Learning
- Meta-Learning Representations for Continual Learning
- Meta-Learning with Implicit Gradients
- Meta Learning with Relational Information for Short Sequences
- Metamers of neural networks reveal divergence from human perceptual systems
- MetaQuant: Learning to Quantize by Learning to Penetrate Non-differentiable Quantization
- Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition
- Meta-Surrogate Benchmarking for Hyperparameter Optimization
- Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting
- Metric Learning for Adversarial Robustness
- Minding the Gap: Between Fairness and Ethics
- Minimal Variance Sampling in Stochastic Gradient Boosting
- Minimax Optimal Estimation of Approximate Differential Privacy on Neighboring Databases
- Minimizers of the Empirical Risk and Risk Monotonicity
- Minimum Stein Discrepancy Estimators
- Mining GOLD Samples for Conditional GANs
- MintNet: Building Invertible Neural Networks with Masked Convolutions
- Missing Not at Random in Matrix Completion: The Effectiveness of Estimating Missingness Probabilities Under a Low Nuclear Norm Assumption
- MixMatch: A Holistic Approach to Semi-Supervised Learning
- Mixtape: Breaking the Softmax Bottleneck Efficiently
- ML For Systems
- MLSys: Workshop on Systems for ML
- Möbius Transformation for Fast Inner Product Search on Graph
- Model-Based Reinforcement Learning with Adversarial Training for Online Recommendation
- Model Compression with Adversarial Robustness: A Unified Optimization Framework
- Modeling Conceptual Understanding in Image Reference Games
- Modeling Dynamic Functional Connectivity with Latent Factor Gaussian Processes
- Modeling Expectation Violation in Intuitive Physics with Coarse Probabilistic Object Representations
- Modeling Tabular data using Conditional GAN
- Modeling Uncertainty by Learning a Hierarchy of Deep Neural Connections
- Modelling heterogeneous distributions with an Uncountable Mixture of Asymmetric Laplacians
- Modelling the Dynamics of Multiagent Q-Learning in Repeated Symmetric Games: a Mean Field Theoretic Approach
- Model Selection for Contextual Bandits
- Model Similarity Mitigates Test Set Overuse
- Modular Universal Reparameterization: Deep Multi-task Learning Across Diverse Domains
- Momentum-Based Variance Reduction in Non-Convex SGD
- MonoForest framework for tree ensemble analysis
- More Is Less: Learning Efficient Video Representations by Big-Little Network and Depthwise Temporal Aggregation
- Mo' States Mo' Problems: Emergency Stop Mechanisms from Observation
- Multi-Agent Common Knowledge Reinforcement Learning
- Multiagent Evaluation under Incomplete Information
- Multiclass Learning from Contradictions
- Multiclass Performance Metric Elicitation
- Multi-Criteria Dimensionality Reduction with Applications to Fairness
- Multi-label Co-regularization for Semi-supervised Facial Action Unit Recognition
- Multilabel reductions: what is my loss optimising?
- Multi-mapping Image-to-Image Translation via Learning Disentanglement
- Multi-marginal Wasserstein GAN
- Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation
- Multi-objective Bayesian optimisation with preferences over objectives
- Multi-objects Generation with Amortized Structural Regularization
- Multiple Futures Prediction
- Multi-relational Poincaré Graph Embeddings
- Multi-resolution Multi-task Gaussian Processes
- Multi-Resolution Weak Supervision for Sequential Data
- Multi-source Domain Adaptation for Semantic Segmentation
- Multi-task Learning for Aggregated Data using Gaussian Processes
- Multivariate Distributionally Robust Convex Regression under Absolute Error Loss
- Multivariate Sparse Coding of Nonstationary Covariances with Gaussian Processes
- Multivariate Triangular Quantile Maps for Novelty Detection
- Multiview Aggregation for Learning Category-Specific Shape Reconstruction
- Multi-View Reinforcement Learning
- Multiway clustering via tensor block models
- muSSP: Efficient Min-cost Flow Algorithm for Multi-object Tracking
- Mutually Regressive Point Processes
- NAOMI: Non-Autoregressive Multiresolution Sequence Imputation
- NAT: Neural Architecture Transformer for Accurate and Compact Architectures
- (Nearly) Efficient Algorithms for the Graph Matching Problem on Correlated Random Graphs
- Nearly Tight Bounds for Robust Proper Learning of Halfspaces with a Margin
- Near Neighbor: Who is the Fairest of Them All?
- Near-Optimal Reinforcement Learning in Dynamic Treatment Regimes
- Necessary and Sufficient Geometries for Gradient Methods
- Network Pruning via Transformable Architecture Search
- Neural Attribution for Semantic Bug-Localization in Student Programs
- Neural Diffusion Distance for Image Segmentation
- Neural Jump Stochastic Differential Equations
- Neural Lyapunov Control
- Neural Machine Translation with Soft Prototype
- Neural Multisensory Scene Inference
- Neural networks grown and self-organized by noise
- Neural Networks with Cheap Differential Operators
- Neural Proximal/Trust Region Policy Optimization Attains Globally Optimal Policy
- Neural Relational Inference with Fast Modular Meta-learning
- Neural Shuffle-Exchange Networks - Sequence Processing in O(n log n) Time
- Neural Similarity Learning
- Neural Spline Flows
- Neural Taskonomy: Inferring the Similarity of Task-Derived Representations from Brain Activity
- Neural Temporal-Difference Learning Converges to Global Optima
- NeurIPS Workshop on Machine Learning for Creativity and Design 3.0
- Neuropathic Pain Diagnosis Simulator for Causal Discovery Algorithm Evaluation
- NeurVPS: Neural Vanishing Point Scanning via Conic Convolution
- New In Machine Learning
- N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules
- NNgen: A Model-Specific Hardware Synthesis Compiler for Deep Neural Network
- Noise-tolerant fair classification
- Non-asymptotic Analysis of Stochastic Methods for Non-Smooth Non-Convex Regularized Problems
- Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs
- Non-Asymptotic Pure Exploration by Solving Games
- Nonconvex Low-Rank Symmetric Tensor Completion from Noisy Data
- Non-Cooperative Inverse Reinforcement Learning
- Nonlinear scaling of resource allocation in sensory bottlenecks
- Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics
- Nonparametric Contextual Bandits in Metric Spaces with Unknown Metric
- Nonparametric Density Estimation & Convergence Rates for GANs under Besov IPM Losses
- Nonparametric Regressive Point Processes Based on Conditional Gaussian Processes
- Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning
- Nonstochastic Multiarmed Bandits with Unrestricted Delays
- Nonzero-sum Adversarial Hypothesis Testing Games
- No-Press Diplomacy: Modeling Multi-Agent Gameplay
- No Pressure! Addressing the Problem of Local Minima in Manifold Learning Algorithms
- No-Regret Learning in Unknown Games with Correlated Payoffs
- Normalization Helps Training of Quantized LSTM
- Novel positional encodings to enable tree-based transformers
- Numerically Accurate Hyperbolic Embeddings Using Tiling-Based Models
- Object landmark discovery through unsupervised adaptation
- ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models
- Oblivious Sampling Algorithms for Private Data Analysis
- ODE2VAE: Deep generative second order ODEs with Bayesian neural networks
- Offline Contextual Bandits with High Probability Fairness Guarantees
- Offline Contextual Bayesian Optimization
- Off-Policy Evaluation via Off-Policy Classification
- On Adversarial Mixup Resynthesis
- On Differentially Private Graph Sparsification and Applications
- On Distributed Averaging for Stochastic k-PCA
- One-on-one fitness training with an AI avatar
- One-Shot Object Detection with Co-Attention and Co-Excitation
- One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers
- On Exact Computation with an Infinitely Wide Neural Net
- On Fenchel Mini-Max Learning
- On Human-Aligned Risk Minimization
- On Lazy Training in Differentiable Programming
- On Learning Over-parameterized Neural Networks: A Functional Approximation Perspective
- Online Continual Learning with Maximal Interfered Retrieval
- Online Continuous Submodular Maximization: From Full-Information to Bandit Feedback
- Online Convex Matrix Factorization with Representative Regions
- Online EXP3 Learning in Adversarial Bandits with Delayed Feedback
- Online Forecasting of Total-Variation-bounded Sequences
- Online Learning via the Differential Privacy Lens
- Online Markov Decoding: Lower Bounds and Near-Optimal Approximation Algorithms
- Online Normalization for Training Neural Networks
- Online Optimal Control with Linear Dynamics and Predictions: Algorithms and Regret Analysis
- Online Prediction of Switching Graph Labelings with Cluster Specialists
- Online sampling from log-concave distributions
- Online Stochastic Shortest Path with Bandit Feedback and Unknown Transition Function
- Online-Within-Online Meta-Learning
- On Making Stochastic Classifiers Deterministic
- On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks
- On Relating Explanations and Adversarial Examples
- On Robustness of Principal Component Regression
- On Robustness to Adversarial Examples and Polynomial Optimization
- On Sample Complexity Upper and Lower Bounds for Exact Ranking from Noisy Comparisons
- On Single Source Robustness in Deep Fusion Models
- On Testing for Biases in Peer Review
- On the Accuracy of Influence Functions for Measuring Group Effects
- On the Calibration of Multiclass Classification with Rejection
- On The Classification-Distortion-Perception Tradeoff
- On the convergence of single-call stochastic extra-gradient methods
- On the Convergence Rate of Training Recurrent Neural Networks
- On the Correctness and Sample Complexity of Inverse Reinforcement Learning
- On the Curved Geometry of Accelerated Optimization
- On the Downstream Performance of Compressed Word Embeddings
- On the equivalence between graph isomorphism testing and function approximation with GNNs
- On the Expressive Power of Deep Polynomial Neural Networks
- On the Fairness of Disentangled Representations
- On the Global Convergence of (Fast) Incremental Expectation Maximization Methods
- On the Hardness of Robust Classification
- On the Inductive Bias of Neural Tangent Kernels
- On the Ineffectiveness of Variance Reduced Optimization for Deep Learning
- On the (In)fidelity and Sensitivity of Explanations
- On the number of variables to use in principal component regression
- On the Optimality of Perturbations in Stochastic and Adversarial Multi-armed Bandit Problems
- On the Power and Limitations of Random Features for Understanding Neural Networks
- On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Dataset
- On the Utility of Learning about Humans for Human-AI Coordination
- On the Value of Target Data in Transfer Learning
- On Tractable Computation of Expected Predictions
- On two ways to use determinantal point processes for Monte Carlo integration
- Optimal Analysis of Subset-Selection Based L_p Low-Rank Approximation
- Optimal Best Markovian Arm Identification with Fixed Confidence
- Optimal Decision Tree with Noisy Outcomes
- Optimal Pricing in Repeated Posted-Price Auctions with Different Patience of the Seller and the Buyer
- Optimal Sampling and Clustering in the Stochastic Block Model
- Optimal Sketching for Kronecker Product Regression and Low Rank Approximation
- Optimal Sparse Decision Trees
- Optimal Sparsity-Sensitive Bounds for Distributed Mean Estimation
- Optimal Statistical Rates for Decentralised Non-Parametric Regression with Linear Speed-Up
- Optimal Stochastic and Online Learning with Individual Iterates
- Optimal Transport for Machine Learning
- Optimistic Distributionally Robust Optimization for Nonparametric Likelihood Approximation
- Optimistic Regret Minimization for Extensive-Form Games via Dilated Distance-Generating Functions
- Optimizing Generalized PageRank Methods for Seed-Expansion Community Detection
- Optimizing Generalized Rate Metrics with Three Players
- Oracle-Efficient Algorithms for Online Linear Optimization with Bandit Feedback
- Ordered Memory
- Order Optimal One-Shot Distributed Learning
- Ouroboros: On Accelerating Training of Transformer-Based Language Models
- Outlier Detection and Robust PCA Using a Convex Measure of Innovation
- Outlier-robust estimation of a sparse linear model using ℓ1-penalized Huber's M-estimator
- Outlier-Robust High-Dimensional Sparse Estimation via Iterative Filtering
- PAC-Bayes under potentially heavy tails
- PAC-Bayes Un-Expected Bernstein Inequality
- Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates
- Paradoxes in Fair Machine Learning
- Parameter elimination in particle Gibbs sampling
- Paraphrase Generation with Latent Bag of Words
- Pareto Multi-Task Learning
- Park: An Open Platform for Learning-Augmented Computer Systems
- Partially Encrypted Deep Learning using Functional Encryption
- Partitioning Structure Learning for Segmented Linear Regression Trees
- Passcode: A cooperative word guessing game between a human and AI agent
- PasteGAN: A Semi-Parametric Method to Generate Image from Scene Graph
- PC-Fairness: A Unified Framework for Measuring Causality-based Fairness
- Perceiving the arrow of time in autoregressive motion
- Perception as generative reasoning: structure, causality, probability
- Personalizing Many Decisions with High-Dimensional Covariates
- PerspectiveNet: 3D Object Detection from a Single RGB Image via Perspective Points
- PerspectiveNet: A Scene-consistent Image Generator for New View Synthesis in Real Indoor Environments
- Phase Transitions and Cyclic Phenomena in Bandits with Switching Constraints
- PHYRE: A New Benchmark for Physical Reasoning
- PIDForest: Anomaly Detection via Partial Identification
- Piecewise Strong Convexity of Neural Networks
- Planning in entropy-regularized Markov decision processes and games
- Planning with Goal-Conditioned Policies
- Poincaré Recurrence, Cycles and Spurious Equilibria in Gradient-Descent-Ascent for Non-Convex Non-Concave Zero-Sum Games
- PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation
- Point-Voxel CNN for Efficient 3D Deep Learning
- Poisson-Minibatching for Gibbs Sampling with Convergence Rate Guarantees
- Poisson-Randomized Gamma Dynamical Systems
- Policy Continuation with Hindsight Inverse Dynamics
- Policy Evaluation with Latent Confounders via Optimal Balance
- Policy Learning for Fairness in Ranking
- Policy Optimization Provably Converges to Nash Equilibria in Zero-Sum Linear Quadratic Games
- Policy Poisoning in Batch Reinforcement Learning and Control
- Polynomial Cost of Adaptation for X-Armed Bandits
- Positional Normalization
- Positive-Unlabeled Compression on the Cloud
- Post training 4-bit quantization of convolutional networks for rapid-deployment
- Power analysis of knockoff filters for correlated designs
- Powerset Convolutional Neural Networks
- PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization
- Practical and Consistent Estimation of f-Divergences
- Practical Deep Learning with Bayesian Principles
- Practical Differentially Private Top-k Selection with Pay-what-you-get Composition
- Practical Two-Step Lookahead Bayesian Optimization
- Precision-Recall Balanced Topic Modelling
- Predicting the Politics of an Image Using Webly Supervised Data
- Prediction of Spatial Point Processes: Regularized Method with Out-of-Sample Guarantees
- Preference-Based Batch and Sequential Teaching: Towards a Unified View of Models
- Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks
- Primal-Dual Block Generalized Frank-Wolfe
- Principal Component Projection and Regression in Nearly Linear Time through Asymmetric SVRG
- Prior-Free Dynamic Auctions with Low Regret Buyers
- Privacy Amplification by Mixing and Diffusion Mechanisms
- Privacy in Machine Learning (PriML)
- Privacy-Preserving Classification of Personal Text Messages with Secure Multi-Party Computation
- Privacy-Preserving Q-Learning with Functional Noise in Continuous Spaces
- Private Hypothesis Selection
- Private Learning Implies Online Learning: An Efficient Reduction
- Private Stochastic Convex Optimization with Optimal Rates
- Private Testing of Distributions via Sample Permutations
- PRNet: Self-Supervised Learning for Partial-to-Partial Registration
- Probabilistic Logic Neural Networks for Reasoning
- Probabilistic Watershed: Sampling all spanning forests for seeded segmentation and semi-supervised learning
- Procrastinating with Confidence: Near-Optimal, Anytime, Adaptive Algorithm Configuration
- Program Synthesis and Semantic Parsing with Learned Code Idioms
- Program Transformations for ML
- Progressive Augmentation of GANs
- Project BB: Bringing AI to the Command Line
- Projected Stein Variational Newton: A Fast and Scalable Bayesian Inference Method in High Dimensions
- Propagating Uncertainty in Reinforcement Learning via Wasserstein Barycenters
- Provable Certificates for Adversarial Examples: Fitting a Ball in the Union of Polytopes
- Provable Gradient Variance Guarantees for Black-Box Variational Inference
- Provable Non-linear Inductive Matrix Completion
- Provably Efficient Q-learning with Function Approximation via Distribution Shift Error Checking Oracle
- Provably Efficient Q-Learning with Low Switching Cost
- Provably Global Convergence of Actor-Critic: A Case for Linear Quadratic Regulator with Ergodic Cost
- Provably Powerful Graph Networks
- Provably robust boosted decision stumps and trees against adversarial attacks
- Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers
- Pseudo-Extended Markov chain Monte Carlo
- Pure Exploration with Multiple Correct Answers
- Push-pull Feedback Implements Hierarchical Information Retrieval Efficiently
- Putting An End to End-to-End: Gradient-Isolated Learning of Representations
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- q-means: A quantum algorithm for unsupervised machine learning
- Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification and Local Computations
- Quadratic Video Interpolation
- Quality Aware Generative Adversarial Networks
- Quantum Embedding of Knowledge for Reasoning
- Quantum Entropy Scoring for Fast Robust Mean Estimation and Improved Outlier Detection
- Quantum Wasserstein Generative Adversarial Networks
- Quaternion Knowledge Graph Embeddings
- R2D2: Reliable and Repeatable Detector and Descriptor
- Random deep neural networks are biased towards simple functions
- Random Path Selection for Continual Learning
- Random Projections and Sampling Algorithms for Clustering of High-Dimensional Polygonal Curves
- Random Projections with Asymmetric Quantization
- Random Quadratic Forms with Dependence: Applications to Restricted Isometry and Beyond
- Random Tessellation Forests
- Rapid Convergence of the Unadjusted Langevin Algorithm: Isoperimetry Suffices
- Rates of Convergence for Large-scale Nearest Neighbor Classification
- Real Neurons & Hidden Units: future directions at the intersection of neuroscience and AI
- Real Time CFD simulations with 3D Mesh Convolutional Networks
- Realtime Modeling and Anomaly Detection in Multivariate Data Streams
- Real-Time Reinforcement Learning
- Reconciling meta-learning and continual learning with online mixtures of tasks
- Reconciling λ-Returns with Experience Replay
- Recovering Bandits
- Recurrent Kernel Networks
- Recurrent Registration Neural Networks for Deformable Image Registration
- Recurrent Space-time Graph Neural Networks
- Reducing Noise in GAN Training with Variance Reduced Extragradient
- Reducing the variance in online optimization by transporting past gradients
- Re-examination of the Role of Latent Variables in Sequence Modeling
- Reflection Separation using a Pair of Unpolarized and Polarized Images
- Region Mutual Information Loss for Semantic Segmentation
- Region-specific Diffeomorphic Metric Mapping
- Regression Planning Networks
- Regret Bounds for Learning State Representations in Reinforcement Learning
- Regret Bounds for Thompson Sampling in Episodic Restless Bandit Problems
- Regret Minimization for Reinforcement Learning by Evaluating the Optimal Bias Function
- Regret Minimization for Reinforcement Learning with Vectorial Feedback and Complex Objectives
- Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel
- Regularized Anderson Acceleration for Off-Policy Deep Reinforcement Learning
- Regularized Gradient Boosting
- Regularized Weighted Low Rank Approximation
- Regularizing Trajectory Optimization with Denoising Autoencoders
- Reinforcement Learning: Past, Present, and Future Perspectives
- Reinforcement Learning with Convex Constraints
- Reliable training and estimation of variance networks
- REM: From Structural Entropy to Community Structure Deception
- Representation Learning and Fairness
- Re-randomized Densification for One Permutation Hashing and Bin-wise Consistent Weighted Sampling
- Residual Flows for Invertible Generative Modeling
- ResNets Ensemble via the Feynman-Kac Formalism to Improve Natural and Robust Accuracies
- Rethinking Deep Neural Network Ownership Verification: Embedding Passports to Defeat Ambiguity Attacks
- Rethinking Generative Mode Coverage: A Pointwise Guaranteed Approach
- Rethinking Kernel Methods for Node Representation Learning on Graphs
- Rethinking the CSC Model for Natural Images
- Retrospectives: A Venue for Self-Reflection in ML Research
- Retrosynthesis Prediction with Conditional Graph Logic Network
- Reverse engineering recurrent networks for sentiment classification reveals line attractor dynamics
- Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness
- Revisiting the Bethe-Hessian: Improved Community Detection in Sparse Heterogeneous Graphs
- Reward Constrained Interactive Recommendation with Natural Language Feedback
- Riemannian batch normalization for SPD neural networks
- Robot-Assisted Hair-Brushing
- Robot Learning: Control and Interaction in the Real World
- Robust AI in Financial Services: Data, Fairness, Explainability, Trustworthiness, and Privacy
- Robust and Communication-Efficient Collaborative Learning
- Robust Attribution Regularization
- Robust Bi-Tempered Logistic Loss Based on Bregman Divergences
- Robust exploration in linear quadratic reinforcement learning
- Robust Multi-agent Counterfactual Prediction
- Robustness to Adversarial Perturbations in Learning from Incomplete Data
- Robustness Verification of Tree-based Models
- Robust Principal Component Analysis with Adaptive Neighbors
- Root Mean Square Layer Normalization
- RSN: Randomized Subspace Newton
- RUBi: Reducing Unimodal Biases for Visual Question Answering
- RUDDER: Return Decomposition for Delayed Rewards
- Saccader: Improving Accuracy of Hard Attention Models for Vision
- Safe Exploration for Interactive Machine Learning
- Safety and Robustness in Decision-making
- Same-Cluster Querying for Overlapping Clusters
- Sample Adaptive MCMC
- Sample Complexity of Learning Mixture of Sparse Linear Regressions
- Sampled Softmax with Random Fourier Features
- Sample Efficient Active Learning of Causal Trees
- Sample-Efficient Deep Reinforcement Learning via Episodic Backward Update
- Sampling Networks and Aggregate Simulation for Online POMDP Planning
- Sampling Sketches for Concave Sublinear Functions of Frequencies
- Scalable Bayesian dynamic covariance modeling with variational Wishart and inverse Wishart processes
- Scalable Bayesian inference of dendritic voltage via spatiotemporal recurrent state space models
- Scalable Deep Generative Relational Model with High-Order Node Dependence
- Scalable Global Optimization via Local Bayesian Optimization
- Scalable Gromov-Wasserstein Learning for Graph Partitioning and Matching
- Scalable inference of topic evolution via models for latent geometric structures
- Scalable Spike Source Localization in Extracellular Recordings using Amortized Variational Inference
- Scalable Structure Learning of Continuous-Time Bayesian Networks from Incomplete Data
- SCAN: A Scalable Neural Networks Framework Towards Compact and Efficient Models
- SCC: Deep Reinforcement Learning Agent plays StarCraft II at competitive human level
- Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations
- Science meets Engineering of Deep Learning
- Screening Sinkhorn Algorithm for Regularized Optimal Transport
- Search-Guided, Lightly-Supervised Training of Structured Prediction Energy Networks
- Search on the Replay Buffer: Bridging Planning and Reinforcement Learning
- Secretary Ranking with Minimal Inversions
- Seeing the Wind: Visual Wind Speed Prediction with a Coupled Convolutional and Recurrent Neural Network
- Selecting causal brain features with a single conditional independence test per feature
- Selecting Optimal Decisions via Distributionally Robust Nearest-Neighbor Regression
- Selecting the independent coordinates of manifolds with large aspect ratios
- Selective Sampling-based Scalable Sparse Subspace Clustering
- Self-attention with Functional Time Representation Learning
- Self-Critical Reasoning for Robust Visual Question Answering
- Self-Routing Capsule Networks
- Self-Supervised Deep Learning on Point Clouds by Reconstructing Space
- Self-supervised GAN: Analysis and Improvement with Multi-class Minimax Game
- Self-Supervised Generalisation with Meta Auxiliary Learning
- Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos
- Semantic-Guided Multi-Attention Localization for Zero-Shot Learning
- Semi-flat minima and saddle points by embedding neural networks to overparameterization
- Semi-Implicit Graph Variational Auto-Encoders
- Semi-Parametric Dynamic Contextual Pricing
- Semi-Parametric Efficient Policy Learning with Continuous Actions
- Semi-supervisedly Co-embedding Attributed Networks
- Sequence Modeling with Unconstrained Generation Order
- Sequential Experimental Design for Transductive Linear Bandits
- Sequential Neural Processes
- Sets and Partitions
- SGD on Neural Networks Learns Functions of Increasing Complexity
- Shadowing Properties of Optimization Algorithms
- Shallow RNN: Accurate Time-series Classification on Resource Constrained Devices
- Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models
- Shaping Belief States with Generative Environment Models for RL
- Shared Mobile-Cloud Inference for Collaborative Intelligence
- Shared Visual Representations in Human and Machine Intelligence
- SHE: A Fast and Accurate Deep Neural Network for Encrypted Data
- SIC-MMAB: Synchronisation Involves Communication in Multiplayer Multi-Armed Bandits
- Sim2real transfer learning for 3D human pose estimation: motion to the rescue
- Single-Model Uncertainties for Deep Learning
- Singleshot : a scalable Tucker tensor decomposition
- Sinkhorn Barycenters with Free Support via Frank-Wolfe Algorithm
- Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices
- Sliced Gromov-Wasserstein
- Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity
- Smart Home Appliances: Chat with your Fridge
- SMILe: Scalable Meta Inverse Reinforcement Learning through Context-Conditional Policies
- Smoothing Structured Decomposable Circuits
- Sobolev Independence Criterion
- Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks
- Social Intelligence
- Solving a Class of Non-Convex Min-Max Games Using Iterative First Order Methods
- Solving graph compression via optimal transport
- Solving Interpretable Kernel Dimensionality Reduction
- Solving inverse problems with deep networks: New architectures, theoretical foundations, and applications
- Space and Time Efficient Kernel Density Estimation in High Dimensions
- Sparse High-Dimensional Isotonic Regression
- Sparse Logistic Regression Learns All Discrete Pairwise Graphical Models
- SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers
- Sparse Variational Inference: Bayesian Coresets from Scratch
- Spatial-Aware Feature Aggregation for Image based Cross-View Geo-Localization
- Spatially Aggregated Gaussian Processes with Multivariate Areal Outputs
- Specific and Shared Causal Relation Modeling and Mechanism-Based Clustering
- Spectral Modification of Graphs for Improved Spectral Clustering
- Spherical Text Embedding
- SpiderBoost and Momentum: Faster Variance Reduction Algorithms
- Spike-Train Level Backpropagation for Training Deep Recurrent Spiking Neural Networks
- Splitting Steepest Descent for Growing Neural Architectures
- SPoC: Search-based Pseudocode to Code
- SSRGD: Simple Stochastic Recursive Gradient Descent for Escaping Saddle Points
- Stability of Graph Scattering Transforms
- Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction
- Stacked Capsule Autoencoders
- Stagewise Training Accelerates Convergence of Testing Error Over SGD
- Stand-Alone Self-Attention in Vision Models
- STAR-Caps: Capsule Networks with Straight-Through Attentive Routing
- State Aggregation Learning from Markov Transition Data
- Statistical Analysis of Nearest Neighbor Methods for Anomaly Detection
- Statistical bounds for entropic optimal transport: sample complexity and the central limit theorem
- Statistical-Computational Tradeoff in Single Index Models
- Statistical Model Aggregation via Parameter Matching
- Staying up to Date with Online Content Changes Using Reinforcement Learning for Scheduling
- Stein Variational Gradient Descent With Matrix-Valued Kernels
- Stochastic Bandits with Context Distributions
- Stochastic Continuous Greedy ++: When Upper and Lower Bounds Match
- Stochastic Frank-Wolfe for Composite Convex Minimization
- Stochastic Gradient Hamiltonian Monte Carlo Methods with Recursive Variance Reduction
- Stochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic Rates
- Stochastic Runge-Kutta Accelerates Langevin Monte Carlo and Beyond
- Stochastic Shared Embeddings: Data-driven Regularization of Embedding Layers
- Stochastic Variance Reduced Primal Dual Algorithms for Empirical Composition Optimization
- Strategizing against No-regret Learners
- Streaming Bayesian Inference for Crowdsourced Classification
- Streamlit, a new app framework for machine learning tools
- STREETS: A Novel Camera Network Dataset for Traffic Flow
- Structured and Deep Similarity Matching via Structured and Deep Hebbian Networks
- Structured Graph Learning Via Laplacian Spectral Constraints
- Structured Prediction with Projection Oracles
- Structured Variational Inference in Continuous Cox Process Models
- Structure Learning with Side Information: Sample Complexity
- Submodular Function Minimization with Noisy Evaluation Oracle
- Subquadratic High-Dimensional Hierarchical Clustering
- Subspace Attack: Exploiting Promising Subspaces for Query-Efficient Black-box Attacks
- Subspace Detours: Building Transport Plans that are Optimal on Subspace Projections
- Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning
- SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems
- Superposition of many models into one
- Superset Technique for Approximate Recovery in One-Bit Compressed Sensing
- Surfing: Iterative Optimization Over Incrementally Trained Deep Networks
- Surrogate Objectives for Batch Policy Optimization in One-step Decision Making
- Surround Modulation: A Bio-inspired Connectivity Structure for Convolutional Neural Networks
- Symmetry-adapted generation of 3d point sets for the targeted discovery of molecules
- Symmetry-Based Disentangled Representation Learning requires Interaction with Environments
- Synthetic Control
- SySCD: A System-Aware Parallel Coordinate Descent Algorithm
- TAB-VCR: Tags and Attributes based Visual Commonsense Reasoning Baselines
- Tackling Climate Change with ML
- Teaching Multiple Concepts to a Forgetful Learner
- Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations.
- Tensor Monte Carlo: Particle Methods for the GPU era
- Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes
- Test of Time
- Test of Time: Dual Averaging Method for Regularized Stochastic Learning and Online Optimization
- The Broad Optimality of Profile Maximum Likelihood
- The Case for Evaluating Causal Models Using Interventional Measures and Empirical Data
- The Cells Out of Sample (COOS) dataset and benchmarks for measuring out-of-sample generalization of image classifiers
- The continuous Bernoulli: fixing a pervasive error in variational autoencoders
- The Convergence Rate of Neural Networks for Learned Functions of Different Frequencies
- The Fairness of Risk Scores Beyond Classification: Bipartite Ranking and the XAUC Metric
- The Functional Neural Process
- The Geometry of Deep Networks: Power Diagram Subdivision
- The Impact of Regularization on High-dimensional Logistic Regression
- The Implicit Bias of AdaGrad on Separable Data
- The Implicit Metropolis-Hastings Algorithm
- The Label Complexity of Active Learning from Observational Data
- The Landscape of Non-convex Empirical Risk with Degenerate Population Risk
- The Normalization Method for Alleviating Pathological Sharpness in Wide Neural Networks
- The Optimization Foundations of Reinforcement Learning
- The Option Keyboard: Combining Skills in Reinforcement Learning
- The Option Keyboard: Combining Skills in Reinforcement Learning
- Theoretical Analysis of Adversarial Learning: A Minimax Approach
- Theoretical evidence for adversarial robustness through randomization
- Theoretical Limits of Pipeline Parallel Optimization and Application to Distributed Deep Learning
- The Parameterized Complexity of Cascading Portfolio Scheduling
- The Point Where Reality Meets Fantasy: Mixed Adversarial Generators for Image Splice Detection
- The Randomized Midpoint Method for Log-Concave Sampling
- The spiked matrix model with generative priors
- The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure For Least Squares
- The Synthesis of XNOR Recurrent Neural Networks with Stochastic Logic
- The Thermodynamic Variational Objective
- The third Conversational AI workshop – today's practice and tomorrow's potential
- Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting
- Think out of the "Box": Generically-Constrained Asynchronous Composite Optimization and Hedging
- Thinning for Accelerating the Learning of Point Processes
- Third-Person Visual Imitation Learning via Decoupled Hierarchical Controller
- This Looks Like That: Deep Learning for Interpretable Image Recognition
- Thompson Sampling and Approximate Inference
- Thompson Sampling for Multinomial Logit Contextual Bandits
- Thompson Sampling with Information Relaxation Penalties
- Thresholding Bandit with Optimal Aggregate Regret
- Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifiers
- Tight Dimensionality Reduction for Sketching Low Degree Polynomial Kernels
- Tight Dimension Independent Lower Bound on the Expected Convergence Rate for Diminishing Step Sizes in SGD
- Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies
- Tight Sample Complexity of Learning One-hidden-layer Convolutional Neural Networks
- Time/Accuracy Tradeoffs for Learning a ReLU with respect to Gaussian Marginals
- Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence
- Time-series Generative Adversarial Networks
- Topology-Preserving Deep Image Segmentation
- Toronto Annotation Suite
- Total Least Squares Regression in Input Sparsity Time
- Toward a Characterization of Loss Functions for Distribution Learning
- Towards Automatic Concept-based Explanations
- Towards a Zero-One Law for Column Subset Selection
- Towards closing the gap between the theory and practice of SVRG
- Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks
- Towards Hardware-Aware Tractable Learning of Probabilistic Models
- Towards Interpretable Reinforcement Learning Using Attention Augmented Agents
- Towards modular and programmable architecture search
- Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling
- Towards Practical Alternating Least-Squares for CCA
- Towards Understanding the Importance of Shortcut Connections in Residual Networks
- Training Image Estimators without Image Ground Truth
- Training Language GANs from Scratch
- Trajectory of Alternating Direction Method of Multipliers and Adaptive Acceleration
- Transductive Zero-Shot Learning with Visual Structure Constraint
- Transferable Normalization: Towards Improving Transferability of Deep Neural Networks
- Transfer Anomaly Detection by Inferring Latent Domain Representations
- Transfer Learning via Minimizing the Performance Gap Between Domains
- Transfusion: Understanding Transfer Learning for Medical Imaging
- Tree-Sliced Variants of Wasserstein Distances
- Triad Constraints for Learning Causal Structure of Latent Variables
- Trivializations for Gradient-Based Optimization on Manifolds
- Trust Region-Guided Proximal Policy Optimization
- Turbo Autoencoder: Deep learning based channel codes for point-to-point communication channels
- Twin Auxilary Classifiers GAN
- Two Generator Game: Learning to Sample via Linear Goodness-of-Fit Test
- Two Time-scale Off-Policy TD Learning: Non-asymptotic Analysis over Markovian Samples
- Ultra Fast Medoid Identification via Correlated Sequential Halving
- Ultrametric Fitting by Gradient Descent
- Uncertainty-based Continual Learning with Adaptive Regularization
- Uncertainty on Asynchronous Time Event Prediction
- Unconstrained Monotonic Neural Networks
- Uncoupled Regression from Pairwise Comparison Data
- Understanding and Improving Layer Normalization
- Understanding Attention and Generalization in Graph Neural Networks
- Understanding Sparse JL for Feature Hashing
- Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology
- Understanding the Role of Momentum in Stochastic Gradient Methods
- Unified Language Model Pre-training for Natural Language Understanding and Generation
- Unified Sample-Optimal Property Estimation in Near-Linear Time
- Uniform convergence may be unable to explain generalization in deep learning
- Uniform Error Bounds for Gaussian Process Regression with Application to Safe Control
- Universal Approximation of Input-Output Maps by Temporal Convolutional Nets
- Universal Boosting Variational Inference
- Universal Invariant and Equivariant Graph Neural Networks
- Universality and individuality in neural dynamics across large populations of recurrent networks
- Universality in Learning from Linear Measurements
- UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization
- Unlabeled Data Improves Adversarial Robustness
- Unlocking Fairness: a Trade-off Revisited
- Unsupervised Co-Learning on G-Manifolds Across Irreducible Representations
- Unsupervised Curricula for Visual Meta-Reinforcement Learning
- Unsupervised Discovery of Temporal Structure in Noisy Data with Dynamical Components Analysis
- Unsupervised Emergence of Egocentric Spatial Structure from Sensorimotor Prediction
- Unsupervised Keypoint Learning for Guiding Class-Conditional Video Prediction
- Unsupervised Learning of Object Keypoints for Perception and Control
- Unsupervised learning of object structure and dynamics from videos
- Unsupervised Meta-Learning for Few-Shot Image Classification
- Unsupervised Object Segmentation by Redrawing
- Unsupervised Scalable Representation Learning for Multivariate Time Series
- Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video
- Unsupervised State Representation Learning in Atari
- Untangling in Invariant Speech Recognition
- Updates of Equilibrium Prop Match Gradients of Backprop Through Time in an RNN with Static Input
- User-Specified Local Differential Privacy in Unconstrained Adaptive Online Learning
- Using a Logarithmic Mapping to Enable Lower Discount Factors in Reinforcement Learning
- Using Embeddings to Correct for Unobserved Confounding in Networks
- Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty
- Using Statistics to Automate Stochastic Optimization
- U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging
- Value Function in Frequency Domain and the Characteristic Value Iteration Algorithm
- Value Propagation for Decentralized Networked Deep Multi-agent Reinforcement Learning
- Variance Reduced Policy Evaluation with Smooth Function Approximation
- Variance Reduction for Matrix Games
- Variance Reduction in Bipartite Experiments through Correlation Clustering
- Variational Bayesian Decision-making for Continuous Utilities
- Variational Bayesian Optimal Experimental Design
- Variational Bayes under Model Misspecification
- Variational Denoising Network: Toward Blind Noise Modeling and Removal
- Variational Graph Recurrent Neural Networks
- Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models
- Variational Structured Semantic Inference for Diverse Image Captioning
- Variational Temporal Abstraction
- Veridical Data Science
- Verified Uncertainty Calibration
- vGraph: A Generative Model for Joint Community Detection and Node Representation Learning
- ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
- VIREL: A Variational Inference Framework for Reinforcement Learning
- Visual Concept-Metaconcept Learning
- Visualizing and Measuring the Geometry of BERT
- Visualizing the PHATE of Neural Networks
- Visually Grounded Interaction and Language
- Volumetric Correspondence Networks for Optical Flow
- Wasserstein Dependency Measure for Representation Learning
- Wasserstein Weisfeiler-Lehman Graph Kernels
- Weakly Supervised Instance Segmentation using the Bounding Box Tightness Prior
- Weight Agnostic Neural Networks
- Weighted Linear Bandits for Non-Stationary Environments
- What Can ResNet Learn Efficiently, Going Beyond Kernels?
- What the Vec? Towards Probabilistically Grounded Embeddings
- When does label smoothing help?
- When to Trust Your Model: Model-Based Policy Optimization
- When to use parametric models in reinforcement learning?
- Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model
- Who is Afraid of Big Bad Minima? Analysis of gradient-flow in spiked matrix-tensor models
- Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition
- Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent
- Workshop on Federated Learning for Data Privacy and Confidentiality
- Workshop on Human-Centric Machine Learning
- Worst-Case Regret Bounds for Exploration via Randomized Value Functions
- Write, Execute, Assess: Program Synthesis with a REPL
- XLNet: Generalized Autoregressive Pretraining for Language Understanding
- XNAS: Neural Architecture Search with Expert Advice
- You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle
- Zero-shot Knowledge Transfer via Adversarial Belief Matching
- Zero-shot Learning via Simultaneous Generating and Learning
- Zero-Shot Semantic Segmentation
- ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization