ICML 2021 Papers

Layout:

mini compact topic detail

Lossless Compression of Efficient Private Local Randomizers

On the Predictability of Pruning Across Scales

Emphatic Algorithms for Deep Reinforcement Learning

Regularizing towards Causal Invariance: Linear Models with Proxies

Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations

How Does Loss Function Affect Generalization Performance of Deep Learning? Application to Human Age Estimation

Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping

TempoRL: Learning When to Act

Tighter Bounds on the Log Marginal Likelihood of Gaussian Process Regression Using Conjugate Gradients

Memory Efficient Online Meta Learning

Adversarial Policy Learning in Two-player Competitive Games

Meta-Cal: Well-controlled Post-hoc Calibration by Ranking

Demonstration-Conditioned Reinforcement Learning for Few-Shot Imitation

Beyond Variance Reduction: Understanding the True Impact of Baselines on Policy Optimization

Equivariant Learning of Stochastic Fields: Gaussian Processes and Steerable Conditional Neural Processes

Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning

Deep Learning for Functional Data Analysis with Adaptive Basis Layers

Three Operator Splitting with a Nonconvex Loss Function

Causality-aware counterfactual confounding adjustment as an alternative to linear residualization in anticausal prediction tasks based on linear learners

DeepWalking Backwards: From Embeddings Back to Graphs

What does LIME really see in images?

Learning to Rehearse in Long Sequence Memorization

ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision

Improving Breadth-Wise Backpropagation in Graph Neural Networks Helps Learning Long-Range Dependencies.

Exact Optimization of Conformal Predictors via Incremental and Decremental Learning

Skew Orthogonal Convolutions

Self-supervised and Supervised Joint Training for Resource-rich Machine Translation

Mixed Cross Entropy Loss for Neural Machine Translation

Dissecting Supervised Constrastive Learning

Hierarchical VAEs Know What They Don’t Know

Optimal Off-Policy Evaluation from Multiple Logging Policies

Regret Minimization in Stochastic Non-Convex Learning via a Proximal-Gradient Approach

Federated Deep AUC Maximization for Hetergeneous Data with a Constant Communication Complexity

Active Learning of Continuous-time Bayesian Networks through Interventions

Variance Reduction via Primal-Dual Accelerated Dual Averaging for Nonsmooth Convex Finite-Sums

Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels

iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients

Multiscale Invertible Generative Networks for High-Dimensional Bayesian Inference

Adaptive Sampling for Best Policy Identification in Markov Decision Processes

Environment Inference for Invariant Learning

Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classification

Approximate Group Fairness for Clustering

Few-Shot Neural Architecture Search

Poolingformer: Long Document Modeling with Pooling Attention

CURI: A Benchmark for Productive Concept Learning Under Uncertainty

Data augmentation for deep learning based accelerated MRI reconstruction with limited data

Context-Aware Online Collective Inference for Templated Graphical Models

Parallelizing Legendre Memory Unit Training

Tilting the playing field: Dynamical loss functions for machine learning

Skill Discovery for Exploration and Planning using Deep Skill Graphs

Learner-Private Convex Optimization

Network Inference and Influence Maximization from Samples

Temporally Correlated Task Scheduling for Sequence Learning

Temporal Predictive Coding For Model-Based Planning In Latent Space

Smooth $p$-Wasserstein Distance: Structure, Empirical Approximation, and Statistical Applications

A Theory of Label Propagation for Subpopulation Shift

Poisson-Randomised DirBN: Large Mutation is Needed in Dirichlet Belief Networks

Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving

Conservative Objective Models for Effective Offline Model-Based Optimization

Selfish Sparse RNN Training

How to Learn when Data Reacts to Your Model: Performative Gradient Descent

A Collective Learning Framework to Boost GNN Expressiveness for Node Classification

On Limited-Memory Subsampling Strategies for Bandits

Learning Randomly Perturbed Structured Predictors for Direct Loss Minimization

Optimal Thompson Sampling strategies for support-aware CVaR bandits

Neural Architecture Search without Training

Discriminative Complementary-Label Learning with Weighted Loss

Dense for the Price of Sparse: Improved Performance of Sparsely Initialized Networks via a Subspace Offset

On Lower Bounds for Standard and Robust Gaussian Process Bandit Optimization

A Functional Perspective on Learning Symmetric Functions with Neural Networks

Oblivious Sketching-based Central Path Method for Linear Programming

Federated Learning under Arbitrary Communication Patterns

Unsupervised Part Representation by Flow Capsules

SigGPDE: Scaling Sparse Gaussian Processes on Sequential Data

Learning Deep Neural Networks under Agnostic Corrupted Supervision

Directional Bias Amplification

Fair Classification with Noisy Protected Attributes: A Framework with Provable Guarantees

Connecting Sphere Manifolds Hierarchically for Regularization

Dual Principal Component Pursuit for Robust Subspace Learning: Theory and Algorithms for a Holistic Approach

Bayesian Optimization over Hybrid Spaces

Detection of Signal in the Spiked Rectangular Models

Streaming Bayesian Deep Tensor Factorization

Deep Reinforcement Learning amidst Continual Structured Non-Stationarity

Compositional Video Synthesis with Action Graphs

Directed Graph Embeddings in Pseudo-Riemannian Manifolds

Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?

Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifold

Representation Matters: Offline Pretraining for Sequential Decision Making

Robust Representation Learning via Perceptual Similarity Metrics

On the difficulty of unbiased alpha divergence minimization

What Are Bayesian Neural Network Posteriors Really Like?

Neural Transformation Learning for Deep Anomaly Detection Beyond Images

On Energy-Based Models with Overparametrized Shallow Neural Networks

Preferential Temporal Difference Learning

Exploiting Shared Representations for Personalized Federated Learning

Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization

Dynamic Game Theoretic Neural Optimizer

Testing Group Fairness via Optimal Transport Projections

Goal-Conditioned Reinforcement Learning with Imagined Subgoals

LogME: Practical Assessment of Pre-trained Models for Transfer Learning

Tensor Programs IIb: Architectural Universality Of Neural Tangent Kernel Training Dynamics

Offline Reinforcement Learning with Fisher Divergence Critic Regularization

Correlation Clustering in Constant Many Parallel Rounds

RATT: Leveraging Unlabeled Data to Guarantee Generalization

Distributed Second Order Methods with Fast Rates and Compressed Communication

Adapting to misspecification in contextual bandits with offline regression oracles

Decoupling Representation Learning from Reinforcement Learning

Task-Optimal Exploration in Linear Dynamical Systems

Finding Relevant Information via a Discrete Fourier Expansion

ADOM: Accelerated Decentralized Optimization Method for Time-Varying Networks

Dash: Semi-Supervised Learning with Dynamic Thresholding

Decision-Making Under Selective Labels: Optimal Finite-Domain Policies and Beyond

Connecting Interpretability and Robustness in Decision Trees through Separation

Self-Damaging Contrastive Learning

On Variational Inference in Biclustering Models

Nonmyopic Multifidelity Acitve Search

Directional Graph Networks

First-Order Methods for Wasserstein Distributionally Robust MDP

REPAINT: Knowledge Transfer in Deep Reinforcement Learning

Addressing Catastrophic Forgetting in Few-Shot Problems

Non-Negative Bregman Divergence Minimization for Deep Direct Density Ratio Estimation

Towards Open-World Recommendation: An Inductive Model-based Collaborative Filtering Approach

Graph Neural Networks Inspired by Classical Iterative Algorithms

Uniform Convergence, Adversarial Spheres and a Simple Remedy

Generating images with sparse representations

Implicit Regularization in Tensor Factorization

Autoencoder Image Interpolation by Shaping the Latent Space

Which transformer architecture fits my data? A vocabulary bottleneck in self-attention

Single Pass Entrywise-Transformed Low Rank Approximation

SGA: A Robust Algorithm for Partial Recovery of Tree-Structured Graphical Models with Noisy Samples

Accelerating Gossip SGD with Periodic Global Averaging

SpreadsheetCoder: Formula Prediction from Semi-structured Context

Compressed Maximum Likelihood

Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment

Policy Analysis using Synthetic Controls in Continuous-Time

Conditional Distributional Treatment Effect with Kernel Conditional Mean Embeddings and U-Statistic Regression

Representation Subspace Distance for Domain Adaptation Regression

Re-understanding Finite-State Representations of Recurrent Policy Networks

Model Distillation for Revenue Optimization: Interpretable Personalized Pricing

Kernel-Based Reinforcement Learning: A Finite-Time Analysis

Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech

More Powerful and General Selective Inference for Stepwise Feature Selection using Homotopy Method

Low-Rank Sinkhorn Factorization

Monte Carlo Variational Auto-Encoders

Solving Challenging Dexterous Manipulation Tasks With Trajectory Optimisation and Reinforcement Learning

Locally Private k-Means in One Round

Optimization Planning for 3D ConvNets

What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?

BANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale Pretraining

Light RUMs

PODS: Policy Optimization via Differentiable Simulation

Recomposing the Reinforcement Learning Building Blocks with Hypernetworks

Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks

Characterizing Fairness Over the Set of Good Models Under Selective Labels

A large-scale benchmark for few-shot program induction and synthesis

CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients

Ensemble Bootstrapping for Q-Learning

Uncovering the Connections Between Adversarial Transferability and Knowledge Transferability

A Scalable Deterministic Global Optimization Algorithm for Clustering Problems

Regularized Online Allocation Problems: Fairness and Beyond

A Proxy Variable View of Shared Confounding

Provable Lipschitz Certification for Generative Models

HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search

Neural SDEs as Infinite-Dimensional GANs

Pointwise Binary Classification with Pairwise Confidence Comparisons

Global Prosody Style Transfer Without Text Transcriptions

A Lower Bound for the Sample Complexity of Inverse Reinforcement Learning

MetaCURE: Meta Reinforcement Learning with Empowerment-Driven Exploration

Affine Invariant Analysis of Frank-Wolfe on Strongly Convex Sets

SparseBERT: Rethinking the Importance Analysis in Self-attention

A Regret Minimization Approach to Iterative Learning Control

1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed

Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision

Efficient Statistical Tests: A Neural Tangent Kernel Approach

Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks

Expressive 1-Lipschitz Neural Networks for Robust Multiple Graph Learning against Adversarial Attacks

ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables

Posterior Value Functions: Hindsight Baselines for Policy Gradient Methods

Few-shot Language Coordination by Modeling Theory of Mind

On the Optimality of Batch Policy Optimization Algorithms

Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills

Faster Kernel Matrix Algebra via Density Estimation

Meta-Thompson Sampling

Simple and Effective VAE Training with Calibrated Decoders

PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration

DANCE: Enhancing saliency maps using decoys

Learning Generalized Intersection Over Union for Dense Pixelwise Prediction

Bayesian Quadrature on Riemannian Data Manifolds

Towards Understanding Learning in Neural Networks with Linear Teachers

Learning from Nested Data with Ornstein Auto-Encoders

When Does Data Augmentation Help With Membership Inference Attacks?

Debiasing Model Updates for Improving Personalized Federated Training

Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design

Reinforcement Learning Under Moral Uncertainty

Elastic Graph Neural Networks

Integrated Defense for Resilient Graph Matching

Latent Programmer: Discrete Latent Codes for Program Synthesis

Toward Better Generalization Bounds with Locally Elastic Stability

CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints

Learning Task Informed Abstractions

Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection

Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design

A Unified Generative Adversarial Network Training via Self-Labeling and Self-Attention

Learning Queueing Policies for Organ Transplantation Allocation using Interpretable Counterfactual Survival Analysis

Generalization Error Bound for Hyperbolic Ordinal Embedding

Can Subnetwork Structure Be the Key to Out-of-Distribution Generalization?

An Algorithm for Stochastic and Adversarial Bandits with Switching Costs

Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning

Composing Normalizing Flows for Inverse Problems

ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training

LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning

Fairness of Exposure in Stochastic Bandits

Non-Autoregressive Electron Redistribution Modeling for Reaction Prediction

A Scalable Second Order Method for Ill-Conditioned Matrix Completion from Few Samples

Testing DNN-based Autonomous Driving Systems under Critical Environmental Conditions

Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap

Householder Sketch for Accurate and Accelerated Least-Mean-Squares Solvers

On Recovering from Modeling Errors Using Testing Bayesian Networks

Learning While Playing in Mean-Field Games: Convergence and Optimality

Data-driven Prediction of General Hamiltonian Dynamics via Learning Exactly-Symplectic Maps

Fast Projection Onto Convex Smooth Constraints

Markpainting: Adversarial Machine Learning meets Inpainting

Online A-Optimal Design and Active Linear Regression

Learning Routines for Effective Off-Policy Reinforcement Learning

Query Complexity of Adversarial Attacks

On Disentangled Representations Learned from Correlated Data

Oops I Took A Gradient: Scalable Sampling for Discrete Distributions

Online Limited Memory Neural-Linear Bandits with Likelihood Matching

Risk-Sensitive Reinforcement Learning with Function Approximation: A Debiasing Approach

Optimizing Black-box Metrics with Iterative Example Weighting

Mandoline: Model Evaluation under Distribution Shift

Provably Correct Optimization and Exploration with Non-linear Policies

Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty Estimation

OmniNet: Omnidirectional Representations from Transformers

Meta Learning for Support Recovery in High-dimensional Precision Matrix Estimation

DG-LMC: A Turn-key and Scalable Synchronous Distributed MCMC Algorithm via Langevin Monte Carlo within Gibbs

Kernel Stein Discrepancy Descent

A Novel Sequential Coreset Method for Gradient Descent Algorithms

Improving Gradient Regularization using Complex-Valued Neural Networks

Data-efficient Hindsight Off-policy Option Learning

Leveraging Good Representations in Linear Contextual Bandits

Adversarial Purification with Score-based Generative Models

Meta-learning Hyperparameter Performance Prediction with Neural Processes

Sequential Domain Adaptation by Synthesizing Distributionally Robust Experts

Towards Better Robust Generalization with Shift Consistency Regularization

Best Model Identification: A Rested Bandit Formulation

Chebyshev Polynomial Codes: Task Entanglement-based Coding for Distributed Matrix Multiplication

Learning Fair Policies in Decentralized Cooperative Multi-Agent Reinforcement Learning

Fast margin maximization via dual acceleration

From Local to Global Norm Emergence: Dissolving Self-reinforcing Substructures with Incremental Social Instruments

Towards Domain-Agnostic Contrastive Learning

Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization

Interpretable Stein Goodness-of-fit Tests on Riemannian Manifold

Tensor Programs IV: Feature Learning in Infinite-Width Neural Networks

Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

Online Submodular Resource Allocation with Applications to Rebalancing Shared Mobility Systems

Unitary Branching Programs: Learnability and Lower Bounds

Cyclically Equivariant Neural Decoders for Cyclic Codes

Optimal Non-Convex Exact Recovery in Stochastic Block Model via Projected Power Method

Generative Adversarial Networks for Markovian Temporal Dynamics: Stochastic Continuous Data Generation

Estimating $\alpha$-Rank from A Few Entries with Low Rank Matrix Completion

Deep Coherent Exploration for Continuous Control

A Differentiable Point Process with Its Application to Spiking Neural Networks

Overcoming Catastrophic Forgetting by Bayesian Generative Regularization

Lenient Regret and Good-Action Identification in Gaussian Process Bandits

Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels

Fixed-Parameter and Approximation Algorithms for PCA with Outliers

Rate-Distortion Analysis of Minimum Excess Risk in Bayesian Learning

FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Analysis

Generalised Lipschitz Regularisation Equals Distributional Robustness

Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision

Targeted Data Acquisition for Evolving Negotiation Agents

BASE Layers: Simplifying Training of Large, Sparse Models

Instabilities of Offline RL with Pre-Trained Neural Representation

RNN with Particle Flow for Probabilistic Spatio-temporal Forecasting

CRFL: Certifiably Robust Federated Learning against Backdoor Attacks

Sharing Less is More: Lifelong Learning in Deep Networks with Selective Layer Transfer

Local Algorithms for Finding Densely Connected Clusters

Near-Optimal Algorithms for Explainable k-Medians and k-Means

Multi-group Agnostic PAC Learnability

Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding

Improved Regret Bound and Experience Replay in Regularized Policy Iteration

Conditional Temporal Neural Processes with Covariance Loss

Structured Convolutional Kernel Networks for Airline Crew Scheduling

Deep Continuous Networks

Efficient Lottery Ticket Finding: Less Data is More

Putting the ``Learning" into Learning-Augmented Algorithms for Frequency Estimation

Classification with Rejection Based on Cost-sensitive Classification

Data Augmentation for Meta-Learning

Signatured Deep Fictitious Play for Mean Field Games with Common Noise

AlphaNet: Improved Training of Supernets with Alpha-Divergence

Sparse within Sparse Gaussian Processes using Neighbor Information

Slot Machines: Discovering Winning Combinations of Random Weights in Neural Networks

Online Unrelated Machine Load Balancing with Predictions Revisited

Connecting Optimal Ex-Ante Collusion in Teams to Extensive-Form Correlation: Faster Algorithms and Positive Complexity Results

An Information-Geometric Distance on the Space of Tasks

Memory-Efficient Pipeline-Parallel DNN Training

Near-Optimal Confidence Sequences for Bounded Random Variables

Personalized Federated Learning using Hypernetworks

GLSearch: Maximum Common Subgraph Detection via Learning to Search

PAC-Learning for Strategic Classification

GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning

GraphDF: A Discrete Flow Model for Molecular Graph Generation

Disentangling Sampling and Labeling Bias for Learning in Large-output Spaces

The Power of Adaptivity for Stochastic Submodular Cover

Decomposable Submodular Function Minimization via Maximum Flow

MC-LSTM: Mass-Conserving LSTM

Sliced Iterative Normalizing Flows

Matrix Sketching for Secure Collaborative Machine Learning

Analysis of stochastic Lanczos quadrature for spectrum approximation

Principal Component Hierarchy for Sparse Quadratic Programs

On the Explicit Role of Initialization on the Convergence and Implicit Bias of Overparametrized Linear Networks

DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning

Multi-Receiver Online Bayesian Persuasion

Equivariant Networks for Pixelized Spheres

On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classification

Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise

Training Recurrent Neural Networks via Forward Propagation Through Time

Fast Sketching of Polynomial Kernels of Polynomial Degree

Differentiable Spatial Planning using Transformers

Dropout: Explicit Forms and Capacity Control

Strategic Classification in the Dark

Stability and Convergence of Stochastic Gradient Clipping: Beyond Lipschitz Continuity and Smoothness

Autoencoding Under Normalization Constraints

Differentially Private Correlation Clustering

Variational Empowerment as Representation Learning for Goal-Conditioned Reinforcement Learning

On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes

Consistent Nonparametric Methods for Network Assisted Covariate Estimation

How could Neural Networks understand Programs?

Conjugate Energy-Based Models

Neural-Pull: Learning Signed Distance Function from Point clouds by Learning to Pull Space onto Surface

Incentivizing Compliance with Algorithmic Instruments

Pure Exploration and Regret Minimization in Matching Bandits

Offline Reinforcement Learning with Pseudometric Learning

Besov Function Approximation and Binary Classification on Low-Dimensional Manifolds Using Convolutional Residual Networks

Contrastive Learning Inverts the Data Generating Process

Scalable Normalizing Flows for Permutation Invariant Densities

A statistical perspective on distillation

NeRF-VAE: A Geometry Aware 3D Scene Generative Model

Alternative Microfoundations for Strategic Classification

On-Policy Deep Reinforcement Learning for the Average-Reward Criterion

Two Heads are Better Than One: Hypergraph-Enhanced Graph Reasoning for Visual Event Ratiocination

Two-way kernel matrix puncturing: towards resource-efficient PCA and spectral clustering

KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation

Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections

One Pass Late Fusion Multi-view Clustering

The Heavy-Tail Phenomenon in SGD

Guided Exploration with Proximal Policy Optimization using a Single Demonstration

Monotonic Robust Policy Optimization with Model Discrepancy

An Identifiable Double VAE For Disentangled Representations

A Framework for Private Matrix Analysis in Sliding Window Model

Unsupervised Representation Learning via Neural Activation Coding

Modeling Hierarchical Structures with Continuous Recursive Neural Networks

Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices

WGAN with an Infinitely Wide Generator Has No Spurious Stationary Points

A Sharp Analysis of Model-based Reinforcement Learning with Self-Play

Interpreting and Disentangling Feature Components of Various Complexity from DNNs

Neural Tangent Generalization Attacks

Provable Robustness of Adversarial Training for Learning Halfspaces with Noise

Model-Free and Model-Based Policy Evaluation when Causality is Uncertain

Efficient Training of Robust Decision Trees Against Adversarial Examples

Distribution-Free Calibration Guarantees for Histogram Binning without Sample Splitting

Quantum algorithms for reinforcement learning with a generative model

Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training

Sharper Generalization Bounds for Clustering

An exact solver for the Weston-Watkins SVM subproblem

Relative Deviation Margin Bounds

12-Lead ECG Reconstruction via Koopman Operators

Cooperative Exploration for Multi-Agent Deep Reinforcement Learning

Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies

MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning

EfficientTTS: An Efficient and High-Quality Text-to-Speech Architecture

Massively Parallel and Asynchronous Tsetlin Machine Architecture Supporting Almost Constant-Time Scaling

A Hybrid Variance-Reduced Method for Decentralized Stochastic Non-Convex Optimization

Projection techniques to update the truncated SVD of evolving matrices with applications

Tightening the Dependence on Horizon in the Sample Complexity of Q-Learning

A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning

LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs

Interpretable Stability Bounds for Spectral Graph Filters

DORO: Distributional and Outlier Robust Optimization

Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding

Parallel tempering on optimized paths

Elementary superexpressive activations

Safe Reinforcement Learning Using Advantage-Based Intervention

Train simultaneously, generalize better: Stability of gradient-based minimax learners

Fundamental Tradeoffs in Distributionally Adversarial Training

PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning

Large Scale Private Learning via Low-rank Reparametrization

Learning and Planning in Average-Reward Markov Decision Processes

WILDS: A Benchmark of in-the-Wild Distribution Shifts

Optimal Complexity in Decentralized Training

Privacy-Preserving Video Classification with Convolutional Neural Networks

Best Arm Identification in Graphical Bilinear Bandits

Detecting Rewards Deterioration in Episodic Reinforcement Learning

Data-Free Knowledge Distillation for Heterogeneous Federated Learning

HAWQ-V3: Dyadic Neural Network Quantization

Parameterless Transductive Feature Re-representation for Few-Shot Learning

Momentum Residual Neural Networks

Understanding Invariance via Feedforward Inversion of Discriminatively Trained Classifiers

Evolving Attention with Residual Convolutions

Graph Cuts Always Find a Global Optimum for Potts Models (With a Catch)

Exponentially Many Local Minima in Quantum Neural Networks

Instance-Optimal Compressed Sensing via Posterior Sampling

Integer Programming for Causal Structure Learning in the Presence of Latent Variables

On Estimation in Latent Variable Models

Representation Matters: Assessing the Importance of Subgroup Allocations in Training Data

Learning Online Algorithms with Distributional Advice

World Model as a Graph: Learning Latent Landmarks for Planning

Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks

EfficientNetV2: Smaller Models and Faster Training

Flow-based Attribution in Graphical Models: A Recursive Shapley Approach

Enhancing Robustness of Neural Networks through Fourier Stabilization

A Distribution-dependent Analysis of Meta Learning

Non-Exponentially Weighted Aggregation: Regret Bounds for Unbounded Loss Functions

Generalization Bounds in the Presence of Outliers: a Median-of-Means Study

Deep Latent Graph Matching

Differentiable Dynamic Quantization with Mixed Precision and Adaptive Resolution

BASGD: Buffered Asynchronous SGD for Byzantine Learning

Near-Optimal Linear Regression under Distribution Shift

Explaining Time Series Predictions with Dynamic Masks

Exploiting structured data for learning contagious diseases under incomplete testing

Learning de-identified representations of prosody from raw audio

Value-at-Risk Optimization with Gaussian Processes

How rotational invariance of common kernels prevents generalization in high dimensions

Locally Adaptive Label Smoothing Improves Predictive Churn

RNNRepair: Automatic RNN Repair via Model-based Analysis

Multi-layered Network Exploration via Random Walks: From Offline Optimization to Online Learning

Training Data Subset Selection for Regression with Controlled Generalization Error

Beyond $log^2(T)$ regret for decentralized bandits in matching markets

Few-Shot Conformal Prediction with Auxiliary Tasks

Quantization Algorithms for Random Fourier Features

Graph Convolution for Semi-Supervised Classification: Improved Linear Separability and Out-of-Distribution Generalization

PID Accelerated Value Iteration Algorithm

Active Learning for Distributionally Robust Level-Set Estimation

Byzantine-Resilient High-Dimensional SGD with Local Iterations on Heterogeneous Data

Offline Meta-Reinforcement Learning with Advantage Weighting

Whitening and Second Order Optimization Both Make Information in the Dataset Unusable During Training, and Can Reduce or Prevent Generalization

An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming

Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning

Improved Corruption Robust Algorithms for Episodic Reinforcement Learning

Don’t Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification

Matrix Completion with Model-free Weighting

Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality

Factor-analytic inverse regression for high-dimension, small-sample dimensionality reduction

SAINT-ACC: Safety-Aware Intelligent Adaptive Cruise Control for Autonomous Vehicles Using Deep Reinforcement Learning

Quantifying Availability and Discovery in Recommender Systems via Stochastic Reachability

Exponential Reduction in Sample Complexity with Learning of Ising Model Dynamics

Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels

The Lipschitz Constant of Self-Attention

SGLB: Stochastic Gradient Langevin Boosting

Training data-efficient image transformers & distillation through attention

Object Segmentation Without Labels with Large-Scale Generative Models

Regularized Submodular Maximization at Scale

Average-Reward Off-Policy Policy Evaluation with Function Approximation

AutoSampling: Search for Effective Data Sampling Schedules

Quantifying and Reducing Bias in Maximum Likelihood Estimation of Structured Anomalies

Lower-Bounded Proper Losses for Weakly Supervised Classification

Differentially Private Densest Subgraph Detection

Domain Generalization using Causal Matching

Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing

Theory of Spectral Method for Union of Subspaces-Based Random Geometry Graph

KO codes: inventing nonlinear encoding and decoding for reliable wireless communication via deep-learning

Probabilistic Programs with Stochastic Conditioning

Inverse Decision Modeling: Learning Interpretable Representations of Behavior

How Do Adam and Training Strategies Help BNNs Optimization

Coded-InvNet for Resilient Prediction Serving Systems

On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths

Asymmetric Loss Functions for Learning with Noisy Labels

Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity

Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning

Breaking the Limits of Message Passing Graph Neural Networks

Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning

Training Adversarially Robust Sparse Networks via Bayesian Connectivity Sampling

Continuous-time Model-based Reinforcement Learning

UCB Momentum Q-learning: Correcting the bias without forgetting

Differentially-Private Clustering of Easy Instances

Online Graph Dictionary Learning

Off-Belief Learning

Approximation Theory Based Methods for RKHS Bandits

Fast active learning for pure exploration in reinforcement learning

Think Global and Act Local: Bayesian Optimisation over High-Dimensional Categorical and Mixed Search Spaces

K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernets

Unsupervised Skill Discovery with Bottleneck Option Learning

One-sided Frank-Wolfe algorithms for saddle problems

Meta-Learning Bidirectional Update Rules

Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message

Concentric mixtures of Mallows models for top-$k$ rankings: sampling and identifiability

Homomorphic Sensing: Sparsity and Noise

Efficient Generative Modelling of Protein Structure Fragments using a Deep Markov Model

Bias-Robust Bayesian Optimization via Dueling Bandits

Distributed Nystr\"{o}m Kernel Learning with Communications

Equivariant message passing for the prediction of tensorial properties and molecular spectra

PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training

SagaNet: A Small Sample Gated Network for Pediatric Cancer Diagnosis

GBHT: Gradient Boosting Histogram Transform for Density Estimation

Imitation by Predicting Observations

Optimal Streaming Algorithms for Multi-Armed Bandits

On the Random Conjugate Kernel and Neural Tangent Kernel

Approximating a Distribution Using Weight Queries

PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization

Revisiting Peng's Q($\lambda$) for Modern Reinforcement Learning

DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning

Learning Optimal Auctions with Correlated Valuations from Samples

Soft then Hard: Rethinking the Quantization in Neural Image Compression

Systematic Analysis of Cluster Similarity Indices: How to Validate Validation Measures

Grid-Functioned Neural Networks

SMG: A Shuffling Gradient-Based Method with Momentum

When All We Need is a Piece of the Pie: A Generic Framework for Optimizing Two-way Partial AUC

PAPRIKA: Private Online False Discovery Rate Control

Near-Optimal Model-Free Reinforcement Learning in Non-Stationary Episodic MDPs

Generative Causal Explanations for Graph Neural Networks

DAGs with No Curl: An Efficient DAG Structure Learning Approach

Improved Confidence Bounds for the Linear Logistic Model and Applications to Bandits

Learning Curves for Analysis of Deep Networks

SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning

Boosting the Throughput and Accelerator Utilization of Specialized CNN Inference Beyond Increasing Batch Size

Information Obfuscation of Graph Neural Networks

Beyond the Pareto Efficient Frontier: Constraint Active Search for Multiobjective Experimental Design

LieTransformer: Equivariant Self-Attention for Lie Groups

Decentralized Riemannian Gradient Descent on the Stiefel Manifold

AutoAttend: Automated Attention Representation Search

Robust Asymmetric Learning in POMDPs

High-Dimensional Gaussian Process Inference with Derivatives

Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning

Multiplying Matrices Without Multiplying

Asymptotics of Ridge Regression in Convolutional Models

Stochastic Sign Descent Methods: New Algorithms and Better Theory

Learning Binary Decision Trees by Argmin Differentiation

Analyzing the tree-layer structure of Deep Forests

Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously

"Hey, that's not an ODE": Faster ODE Adjoints via Seminorms

Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss

High-Performance Large-Scale Image Recognition Without Normalization

Federated Continual Learning with Weighted Inter-client Transfer

Privacy-Preserving Feature Selection with Secure Multiparty Computation

Learning Bounds for Open-Set Learning

Nonparametric Hamiltonian Monte Carlo

Parameter-free Locally Accelerated Conditional Gradients

SG-PALM: a Fast Physically Interpretable Tensor Graphical Model

Learning Intra-Batch Connections for Deep Metric Learning

Graph Mixture Density Networks

Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards

Unsupervised Learning of Visual 3D Keypoints for Control

A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning

Versatile Verification of Tree Ensembles

Bayesian Optimistic Optimisation with Exponentially Decaying Regret

Guarantees for Tuning the Step Size using a Learning-to-Learn Approach

Robust Learning-Augmented Caching: An Experimental Study

Phase Transitions, Distance Functions, and Implicit Neural Representations

Differentiable Particle Filtering via Entropy-Regularized Optimal Transport

Differentially Private Sliced Wasserstein Distance

Global Convergence of Policy Gradient for Linear-Quadratic Mean-Field Control/Game in Continuous Time

Convex Regularization in Monte-Carlo Tree Search

OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation

Towards the Unification and Robustness of Perturbation and Gradient Based Explanations

SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks

Self-Tuning for Data-Efficient Deep Learning

Supervised Tree-Wasserstein Distance

Robust Learning for Data Poisoning Attacks

A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibration

Practical and Private (Deep) Learning Without Sampling or Shuffling

A New Formalism, Method and Open Issues for Zero-Shot Coordination

Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks

Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization

UnICORNN: A recurrent model for learning very long time dependencies

Evaluating the Implicit Midpoint Integrator for Riemannian Hamiltonian Monte Carlo

Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation

Leveraging Language to Learn Program Abstractions and Search Heuristics

Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers

Making transport more robust and interpretable by moving data through a small number of anchor points

Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances

SKIing on Simplices: Kernel Interpolation on the Permutohedral Lattice for Scalable Gaussian Processes

Opening the Blackbox: Accelerating Neural Differential Equations by Regularizing Internal Solver Heuristics

Online Optimization in Games via Control Theory: Connecting Regret, Passivity and Poincaré Recurrence

Strategic Classification Made Practical

Learning to Weight Imperfect Demonstrations

Narrow Margins: Classification, Margins and Fat Tails

Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approach

Grey-box Extraction of Natural Language Models

Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solvers

Deep Generative Learning via Schrödinger Bridge

Multiplicative Noise and Heavy Tails in Stochastic Optimization

Not All Memories are Created Equal: Learning to Forget by Expiring

Large-Margin Contrastive Learning with Distance Polarization Regularizer

Variational (Gradient) Estimate of the Score Function in Energy-based Latent Variable Models

Reward Identification in Inverse Reinforcement Learning

Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processes

PixelTransformer: Sample Conditioned Signal Generation

GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings

Dichotomous Optimistic Search to Quantify Human Perception

Adversarial Option-Aware Hierarchical Imitation Learning

BasisDeVAE: Interpretable Simultaneous Dimensionality Reduction and Feature-Level Clustering with Derivative-Based Variational Autoencoders

Randomized Exploration in Reinforcement Learning with General Value Function Approximation

Adversarial Combinatorial Bandits with General Non-linear Reward Functions

APS: Active Pretraining with Successor Features

Zero-Shot Knowledge Distillation from a Decision-Based Black-Box Model

Functional Space Analysis of Local GAN Convergence

Deciding What to Learn: A Rate-Distortion Approach

Neural Rough Differential Equations for Long Time Series

Cross-domain Imitation from Observations

Adversarial Multi Class Learning under Weak Supervision with Performance Guarantees

Backdoor Scanning for Deep Neural Networks through K-Arm Optimization

Winograd Algorithm for AdderNet

Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs

Provably Strict Generalisation Benefit for Equivariant Models

Continuous Coordination As a Realistic Scenario for Lifelong Learning

EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL

Trees with Attention for Set Prediction Tasks

Infinite-Dimensional Optimization for Zero-Sum Games via Variational Transport

Quasi-global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data

Barlow Twins: Self-Supervised Learning via Redundancy Reduction

Differentially Private Query Release Through Adaptive Projection

Oblivious Sketching for Logistic Regression

Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition

Learning from Similarity-Confidence Data

Label-Only Membership Inference Attacks

Self-Improved Retrosynthetic Planning

A Second look at Exponential and Cosine Step Sizes: Simplicity, Adaptivity, and Performance

Representational aspects of depth and conditioning in normalizing flows

Maximum Mean Discrepancy Test is Aware of Adversarial Attacks

Probabilistic Generating Circuits

KNAS: Green Neural Architecture Search

Sparse and Imperceptible Adversarial Attack via a Homotopy Algorithm

You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling

An Integer Linear Programming Framework for Mining Constraints from Data

Sparsity-Agnostic Lasso Bandit

Optimal Transport Kernels for Sequential and Parallel Neural Architecture Search

Federated Composite Optimization

Randomized Algorithms for Submodular Function Maximization with a $k$-System Constraint

Linear Transformers Are Secretly Fast Weight Programmers

High-dimensional Experimental Design and Kernel Bandits

LAMDA: Label Matching Deep Domain Adaptation

Diffusion Source Identification on Networks with Statistical Confidence

Break-It-Fix-It: Unsupervised Learning for Program Repair

Variational Data Assimilation with a Learned Inverse Observation Operator

A Value-Function-based Interior-point Method for Non-convex Bi-level Optimization

Improved, Deterministic Smoothing for L_1 Certified Robustness

The Power of Log-Sum-Exp: Sequential Density Ratio Matrix Estimation for Speed-Accuracy Optimization

Joining datasets via data augmentation in the label space for neural networks

Explore Visual Concept Formation for Image Classification

Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting

Scalable Certified Segmentation via Randomized Smoothing

Prioritized Level Replay

Efficient Differentiable Simulation of Articulated Bodies

The Logical Options Framework

Self-Paced Context Evaluation for Contextual Reinforcement Learning

Decomposed Mutual Information Estimation for Contrastive Representation Learning

Crowdsourcing via Annotator Co-occurrence Imputation and Provable Symmetric Nonnegative Matrix Factorization

Objective Bound Conditional Gaussian Process for Bayesian Optimization

The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation

Taylor Expansion of Discount Factors

Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization

Zeroth-Order Non-Convex Learning via Hierarchical Dual Averaging

Let's Agree to Degree: Comparing Graph Convolutional Networks in the Message-Passing Framework

Counterfactual Credit Assignment in Model-Free Reinforcement Learning

Temporal Difference Learning as Gradient Splitting

Agnostic Learning of Halfspaces with Gradient Descent via Soft Margins

Spectral vertex sparsifiers and pair-wise spanners over distributed graphs

Multi-Task Reinforcement Learning with Context-based Representations

Muesli: Combining Improvements in Policy Optimization

Feature Clustering for Support Identification in Extreme Regions

A Gradient Based Strategy for Hamiltonian Monte Carlo Hyperparameter Optimization

Newton Method over Networks is Fast up to the Statistical Precision

From Local Structures to Size Generalization in Graph Neural Networks

Estimating Identifiable Causal Effects on Markov Equivalence Class through Double Machine Learning

Towards Open Ad Hoc Teamwork Using Graph-based Policy Learning

HoroPCA: Hyperbolic Dimensionality Reduction via Horospherical Projections

A Novel Method to Solve Neural Knapsack Problems

Self Normalizing Flows

Sparsifying Networks via Subdifferential Inclusion

Label Distribution Learning Machine

Stabilizing Equilibrium Models by Jacobian Regularization

Finding the Stochastic Shortest Path with Low Regret: the Adversarial Cost and Unknown Transition Case

Gaussian Process-Based Real-Time Learning for Safety Critical Applications

Making Paper Reviewing Robust to Bid Manipulation Attacks

Watermarking Deep Neural Networks with Greedy Residuals

Cumulants of Hawkes Processes are Robust to Observation Noise

Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization

Submodular Maximization subject to a Knapsack Constraint: Combinatorial Algorithms with Near-optimal Adaptive Complexity

Ditto: Fair and Robust Federated Learning Through Personalization

Run-Sort-ReRun: Escaping Batch Size Limitations in Sliced Wasserstein Generative Models

Multi-Dimensional Classification via Sparse Label Encoding

Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learning

Annealed Flow Transport Monte Carlo

Active Slices for Sliced Stein Discrepancy

Partially Observed Exchangeable Modeling

Finding k in Latent $k-$ polytope

Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning

Prediction-Centric Learning of Independent Cascade Dynamics from Partial Observations

UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data

Deeply-Debiased Off-Policy Interval Estimation

On Monotonic Linear Interpolation of Neural Network Parameters

Reinforcement Learning with Prototypical Representations

Rissanen Data Analysis: Examining Dataset Characteristics via Description Length

GeomCA: Geometric Evaluation of Data Representations

HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture

Graph Contrastive Learning Automated

CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection

Understanding the Dynamics of Gradient Flow in Overparameterized Linear models

On Robust Mean Estimation under Coordinate-level Corruption

Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity

T-SCI: A Two-Stage Conformal Inference Algorithm with Guaranteed Coverage for Cox-MLP

Perceiver: General Perception with Iterative Attention

Delving into Deep Imbalanced Regression

Scaling Properties of Deep Residual Networks

On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework

Distributionally Robust Optimization with Markovian Data

Understanding Instance-Level Label Noise: Disparate Impacts and Treatments

Intermediate Layer Optimization for Inverse Problems using Deep Generative Models

On Proximal Policy Optimization's Heavy-tailed Gradients

Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline

Model Fusion for Personalized Learning

Density Constrained Reinforcement Learning

Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing

Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting

Near Optimal Reward-Free Reinforcement Learning

Backpropagated Neighborhood Aggregation for Accurate Training of Spiking Neural Networks

Learning Gradient Fields for Molecular Conformation Generation

Off-Policy Confidence Sequences

Almost Optimal Anytime Algorithm for Batched Multi-Armed Bandits

Finite mixture models do not reliably learn the number of components

Accelerating Safe Reinforcement Learning with Constraint-mismatched Baseline Policies

Learning disentangled representations via product manifold projection

Noise and Fluctuation of Finite Learning Rate Stochastic Gradient Descent

Adapting to Delays and Data in Adversarial Multi-Armed Bandits

ACE: Explaining cluster from an adversarial perspective

Pareto GAN: Extending the Representational Power of GANs to Heavy-Tailed Distributions

Confidence-Budget Matching for Sequential Budgeted Learning

Interactive Learning from Activity Description

Stochastic Multi-Armed Bandits with Unrestricted Delay Distributions

Segmenting Hybrid Trajectories using Latent ODEs

Model-based Reinforcement Learning for Continuous Control with Posterior Sampling

Robust Density Estimation from Batches: The Best Things in Life are (Nearly) Free

Stochastic Iterative Graph Matching

Lipschitz normalization for self-attention layers with application to graph neural networks

Inverse Constrained Reinforcement Learning

Keyframe-Focused Visual Imitation Learning

Learning in Nonzero-Sum Stochastic Games with Potentials

The Hintons in your Neural Network: a Quantum Field Theory View of Deep Learning

Function Contrastive Learning of Transferable Meta-Representations

A New Representation of Successor Features for Transfer across Dissimilar Environments

Generalized Doubly Reparameterized Gradient Estimators

A Nullspace Property for Subspace-Preserving Recovery

Self-supervised Graph-level Representation Learning with Local and Global Structure

Probabilistic Sequential Shrinking: A Best Arm Identification Algorithm for Stochastic Bandits with Corruptions

Efficient Message Passing for 0–1 ILPs with Binary Decision Diagrams

Towards Rigorous Interpretations: a Formalisation of Feature Attribution

Dynamic Planning and Learning under Recovering Rewards

Marginal Contribution Feature Importance - an Axiomatic Approach for Explaining Data

Geometric convergence of elliptical slice sampling

GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training

Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information

A Bit More Bayesian: Domain-Invariant Learning with Uncertainty

Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision

Modelling Behavioural Diversity for Learning in Open-Ended Games

Active Deep Probabilistic Subsampling

Resource Allocation in Multi-armed Bandit Exploration: Overcoming Sublinear Scaling with Adaptive Parallelism

Valid Causal Inference with (Some) Invalid Instruments

Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm

Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning

Disambiguation of Weak Supervision leading to Exponential Convergence rates

Towards Practical Mean Bounds for Small Samples

Projection Robust Wasserstein Barycenters

Reinforcement Learning for Cost-Aware Markov Decision Processes

Learning a Universal Template for Few-shot Dataset Generalization

Better Training using Weight-Constrained Stochastic Dynamics

Leveraging Sparse Linear Layers for Debuggable Deep Networks

Logarithmic Regret for Reinforcement Learning with Linear Function Approximation

Dataset Condensation with Differentiable Siamese Augmentation

Consistent regression when oblivious outliers overwhelm

Learning Diverse-Structured Networks for Adversarial Robustness

A Unified Lottery Ticket Hypothesis for Graph Neural Networks

Approximation Theory of Convolutional Architectures for Time Series Modelling

Parallel Droplet Control in MEDA Biochips using Multi-Agent Reinforcement Learning

Bias-Free Scalable Gaussian Processes via Randomized Truncations

Provably Efficient Learning of Transferable Rewards

ConvexVST: A Convex Optimization Approach to Variance-stabilizing Transformation

Differentially Private Quantiles

Training Graph Neural Networks with 1000 Layers

Hyperparameter Selection for Imitation Learning

Active Feature Acquisition with Generative Surrogate Models

Machine Unlearning for Random Forests

Improved OOD Generalization via Adversarial Training and Pretraing

Learning from Biased Data: A Semi-Parametric Approach

Provably End-to-end Label-noise Learning without Anchor Points

Implicit Bias of Linear RNNs

Combinatorial Blocking Bandits with Stochastic Delays

Offline Contextual Bandits with Overparameterized Models

Conformal prediction interval for dynamic time-series

Kernel Continual Learning

Optimal regret algorithm for Pseudo-1d Bandit Convex Optimization

Dueling Convex Optimization

Learning and Planning in Complex Action Spaces

SiameseXML: Siamese Networks meet Extreme Classifiers with 100M Labels

Adversarial Dueling Bandits

On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel Models

Improving Predictors via Combination Across Diverse Task Categories

Is Pessimism Provably Efficient for Offline RL?

A theory of high dimensional regression with arbitrary correlations between input features and target functions: sample complexity, multiple descent curves and a hierarchy of phase transitions

PACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees

Understanding self-supervised learning dynamics without contrastive pairs

On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent

Boosting for Online Convex Optimization

Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning

Model-Targeted Poisoning Attacks with Provable Convergence

Statistical Estimation from Dependent Data

Correcting Exposure Bias for Link Recommendation

A Probabilistic Approach to Neural Network Pruning

Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Exploration

TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL

Discretization Drift in Two-Player Games

Optimizing persistent homology based functions

Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment

Wasserstein Distributional Normalization For Robust Distributional Certification of Noisy Labeled Data

Whittle Networks: A Deep Likelihood Model for Time Series

AGENT: A Benchmark for Core Psychological Reasoning

Moreau-Yosida $f$-divergences

Accurate Post Training Quantization With Small Calibration Sets

Improved Regret Bounds of Bilinear Bandits using Action Space Analysis

Model-Based Reinforcement Learning via Latent-Space Collocation

Learning Node Representations Using Stationary Flow Prediction on Large Payment and Cash Transaction Networks

ChaCha for Online AutoML

Hierarchical Clustering of Data Streams: Scalable Algorithms and Approximation Guarantees

SinIR: Efficient General Image Manipulation with Single Image Reconstruction

Simultaneous Similarity-based Self-Distillation for Deep Metric Learning

Budgeted Heterogeneous Treatment Effect Estimation

Discrete-Valued Latent Preference Matrix Estimation with Graph Side Information

Confidence Scores Make Instance-dependent Label-noise Learning Possible

Whitening for Self-Supervised Representation Learning

Principled Simplicial Neural Networks for Trajectory Prediction

Fused Acoustic and Text Encoding for Multimodal Bilingual Pretraining and Speech Translation

UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning

Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with O(1/k^2) Rate on Squared Gradient Norm

Top-k eXtreme Contextual Bandits with Arm Hierarchy

Inference for Network Regression Models with Community Structure

The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks

BORE: Bayesian Optimization by Density-Ratio Estimation

PHEW : Constructing Sparse Networks that Learn Fast and Generalize Well without Training Data

Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks

A Discriminative Technique for Multiple-Source Adaptation

Online Selection Problems against Constrained Adversary

Fairness for Image Generation with Uncertain Sensitive Attributes

Robust Policy Gradient against Strong Data Corruption

Robust Pure Exploration in Linear Bandits with Limited Budget

Asynchronous Distributed Learning : Adapting to Gradient Delays without Prior Knowledge

RRL: Resnet as representation for Reinforcement Learning

Post-selection inference with HSIC-Lasso

Learning Interaction Kernels for Agent Systems on Riemannian Manifolds

Aggregating From Multiple Target-Shifted Sources

A General Framework For Detecting Anomalous Inputs to DNN Classifiers

A Modular Analysis of Provable Acceleration via Polyak's Momentum: Training a Wide ReLU Network and a Deep Linear Network

Value Alignment Verification

Towards Distraction-Robust Active Visual Tracking

Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Rates

Fairness and Bias in Online Selection

Model Performance Scaling with Multiple Data Sources

Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models

Online Learning in Unknown Markov Games

Revealing the Structure of Deep Neural Networks via Convex Duality

Uncertainty Principles of Encoding GANs

Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation

Understanding and Mitigating Accuracy Disparity in Regression

Megaverse: Simulating Embodied Agents at One Million Experiences per Second

Stability and Generalization of Stochastic Gradient Methods for Minimax Problems

Cross-model Back-translated Distillation for Unsupervised Machine Translation

Revenue-Incentive Tradeoffs in Dynamic Reserve Pricing

End-to-End Learning of Coherent Probabilistic Forecasts for Hierarchical Time Series

Principal Bit Analysis: Autoencoding with Schur-Concave Loss

Improved Algorithms for Agnostic Pool-based Active Classification

Randomized Dimensionality Reduction for Facility Location and Single-Linkage Clustering

Sample-Optimal PAC Learning of Halfspaces with Malicious Noise

Differentially Private Bayesian Inference for Generalized Linear Models

Online Learning for Load Balancing of Unknown Monotone Resource Allocation Games

Generative Video Transformer: Can Objects be the Words?

A Wasserstein Minimax Framework for Mixed Linear Regression

Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning

On a Combination of Alternating Minimization and Nesterov's Momentum

Latent Space Energy-Based Model of Symbol-Vector Coupling for Text Generation and Classification

Sparse Bayesian Learning via Stepwise Regression

Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators

Reasoning Over Virtual Knowledge Bases With Open Predicate Relations

Learning from Noisy Labels with No Change to the Training Process

Bayesian Structural Adaptation for Continual Learning

Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot

DriftSurf: Stable-State / Reactive-State Learning under Concept Drift

Streaming and Distributed Algorithms for Robust Column Subset Selection

Operationalizing Complex Causes: A Pragmatic View of Mediation

Neural Feature Matching in Implicit 3D Representations

From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization

MSA Transformer

Heterogeneous Risk Minimization

Variational Auto-Regressive Gaussian Processes for Continual Learning

Group Fisher Pruning for Practical Network Compression

How Important is the Train-Validation Split in Meta-Learning?

Outlier-Robust Optimal Transport

Learn-to-Share: A Hardware-friendly Transfer Learning Framework Exploiting Computation and Parameter Sharing

Consensus Control for Decentralized Deep Learning

Mixed Nash Equilibria in the Adversarial Examples Game

Active Covering

Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons

Joint Online Learning and Decision-making via Dual Mirror Descent

Attention is not all you need: pure attention loses rank doubly exponentially with depth

Nonparametric Decomposition of Sparse Tensors

Generalization Guarantees for Neural Architecture Search with Train-Validation Split

A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation

Calibrate Before Use: Improving Few-shot Performance of Language Models

I-BERT: Integer-only BERT Quantization

A Language for Counterfactual Generative Models

Thinking Like Transformers

Private Stochastic Convex Optimization: Optimal Rates in L1 Geometry

Multidimensional Scaling: Approximation and Complexity

Discovering symbolic policies with deep reinforcement learning

Learning from History for Byzantine Robust Optimization

Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling

On-the-fly Rectification for Robust Large-Vocabulary Topic Inference

Additive Error Guarantees for Weighted Low Rank Approximation

Problem Dependent View on Structured Thresholding Bandit Problems

Heterogeneity for the Win: One-Shot Federated Clustering

Characterizing Structural Regularities of Labeled Data in Overparameterized Models

Oneshot Differentially Private Top-k Selection

Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with √T Regret

Double-Win Quant: Aggressively Winning Robustness of Quantized Deep Neural Networks via Random Precision Training and Inference

Unifying Vision-and-Language Tasks via Text Generation

Explanations for Monotonic Classifiers.

Towards Tight Bounds on the Sample Complexity of Average-reward MDPs

Measuring Robustness in Deep Learning Based Compressive Sensing

Recovering AES Keys with a Deep Cold Boot Attack

ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks

Optimal Counterfactual Explanations in Tree Ensembles

Learning Neural Network Subspaces

Predict then Interpolate: A Simple Algorithm to Learn Stable Classifiers

Cross-Gradient Aggregation for Decentralized Learning from Non-IID Data

Bayesian Deep Learning via Subnetwork Inference

Solving high-dimensional parabolic PDEs using the tensor train format

Diffusion Earth Mover's Distance and Distribution Embeddings

Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics

A Tale of Two Efficient and Informative Negative Sampling Distributions

Tractable structured natural-gradient descent using local parameterizations

Spectral Normalisation for Deep Reinforcement Learning: An Optimisation Perspective

A Structured Observation Distribution for Generative Biological Sequence Prediction and Forecasting

Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment Restriction

Dynamic Balancing for Model Selection in Bandits and RL

Coach-Player Multi-agent Reinforcement Learning for Dynamic Team Composition

Controlling Graph Dynamics with Reinforcement Learning and Graph Neural Networks

A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups

Neural Symbolic Regression that scales

Label Inference Attacks from Log-loss Scores

A Precise Performance Analysis of Support Vector Regression

On Linear Identifiability of Learned Representations

Generalizable Episodic Memory for Deep Reinforcement Learning

Zoo-Tuning: Adaptive Transfer from A Zoo of Models

Characterizing the Gap Between Actor-Critic and Policy Gradient

DeepReDuce: ReLU Reduction for Fast Private Inference

Learning to Generate Noise for Multi-Attack Robustness

Globally-Robust Neural Networks

MorphVAE: Generating Neural Morphologies from 3D-Walks using a Variational Autoencoder with Spherical Latent Space

Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification

State Entropy Maximization with Random Encoders for Efficient Exploration

EL-Attention: Memory Efficient Lossless Attention for Generation

The Earth Mover's Pinball Loss: Quantiles for Histogram-Valued Regression

GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training

CountSketches, Feature Hashing and the Median of Three

Improved Contrastive Divergence Training of Energy-Based Models

Marginalized Stochastic Natural Gradients for Black-Box Variational Inference

SketchEmbedNet: Learning Novel Concepts by Imitating Drawings

Safe Reinforcement Learning with Linear Function Approximation

Leveraged Weighted Loss for Partial Label Learning

HyperHyperNetwork for the Design of Antenna Arrays

Explainable Automated Graph Representation Learning with Hyperparameter Importance

CARTL: Cooperative Adversarially-Robust Transfer Learning

Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation

MARINA: Faster Non-Convex Distributed Learning with Compression

Parametric Graph for Unimodal Ranking Bandit

No-regret Algorithms for Capturing Events in Poisson Point Processes

Estimation and Quantization of Expected Persistence Diagrams

Follow-the-Regularized-Leader Routes to Chaos in Routing Games

Decentralized Single-Timescale Actor-Critic on Zero-Sum Two-Player Stochastic Games

Towards Understanding and Mitigating Social Biases in Language Models

Unsupervised Co-part Segmentation through Assembly

PipeTransformer: Automated Elastic Pipelining for Distributed Training of Large-scale Models

Implicit rate-constrained optimization of non-decomposable objectives

To be Robust or to be Fair: Towards Fairness in Adversarial Training

Neural Pharmacodynamic State Space Modeling

Adaptive Newton Sketch: Linear-time Optimization with Quadratic Convergence and Effective Hessian Dimensionality

Accuracy, Interpretability, and Differential Privacy via Explainable Boosting

Reinforcement Learning of Implicit and Explicit Control Flow Instructions

SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II

Policy Gradient Bayesian Robust Optimization for Imitation Learning

Online Learning with Optimism and Delay

Blind Pareto Fairness and Subgroup Robustness

Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games

Optimal Estimation of High Dimensional Smooth Additive Function Based on Noisy Observations

Structured World Belief for Reinforcement Learning in POMDP

Improved Denoising Diffusion Probabilistic Models

Prior Image-Constrained Reconstruction using Style-Based Generative Models

Vector Quantized Models for Planning

On the Convergence of Hamiltonian Monte Carlo with Stochastic Gradients

f-Domain Adversarial Learning: Theory and Algorithms

Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning

Automatic variational inference with cascading flows

Mediated Uncoupled Learning: Learning Functions without Direct Input-output Correspondences

Dataset Dynamics via Gradient Flows in Probability Space

Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries

Fast Stochastic Bregman Gradient Methods: Sharp Analysis and Variance Reduction

Link Prediction with Persistent Homology: An Interactive View

Regret and Cumulative Constraint Violation Analysis for Online Convex Optimization with Long Term Constraints

PopSkipJump: Decision-Based Attack for Probabilistic Classifiers

Black-box density function estimation using recursive partitioning

Transfer-Based Semantic Anomaly Detection

Bilevel Optimization: Convergence Analysis and Enhanced Design

Neuro-algorithmic Policies Enable Fast Combinatorial Generalization

Collaborative Bayesian Optimization with Fair Regret

Leveraging Non-uniformity in First-order Non-convex Optimization

Solving Inverse Problems with a Flow-based Noise Model

Trajectory Diversity for Zero-Shot Coordination

Zero-Shot Text-to-Image Generation

Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?

Understanding Failures in Out-of-Distribution Detection with Deep Generative Models

One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning

On the Inherent Regularization Effects of Noise Injection During Training

Learn2Hop: Learned Optimization on Rough Landscapes

A Zeroth-Order Block Coordinate Descent Algorithm for Huge-Scale Black-Box Optimization

Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations

State Relevance for Off-Policy Evaluation

Leveraging Public Data for Practical Private Query Release

Sample Complexity of Robust Linear Classification on Separated Data

Continual Learning in the Teacher-Student Setup: Impact of Task Similarity

Spectral Smoothing Unveils Phase Transitions in Hierarchical Variational Autoencoders

Robust Testing and Estimation under Manipulation Attacks

Policy Caches with Successor Features

Neighborhood Contrastive Learning Applied to Online Patient Monitoring

Value Iteration in Continuous Actions, States and Time

Provable Meta-Learning of Linear Representations

Provably Efficient Algorithms for Multi-Objective Competitive RL

Decoupling Value and Policy for Generalization in Reinforcement Learning

High Confidence Generalization for Reinforcement Learning

Fair Selective Classification Via Sufficiency

SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies

Dimensionality Reduction for the Sum-of-Distances Metric

Synthesizer: Rethinking Self-Attention for Transformer Models

Weight-covariance alignment for adversarially robust neural networks

Robust Unsupervised Learning via L-statistic Minimization

Active Testing: Sample-Efficient Model Evaluation

Reserve Price Optimization for First Price Auctions in Display Advertising

E(n) Equivariant Graph Neural Networks

Demystifying Inductive Biases for (Beta-)VAE Based Architectures

Disentangling syntax and semantics in the brain with deep networks

FOP: Factorizing Optimal Joint Policy of Maximum-Entropy Multi-Agent Reinforcement Learning

Training Quantized Neural Networks to Global Optimality via Semidefinite Programming

Generative Particle Variational Inference via Estimation of Functional Gradients

Size-Invariant Graph Representations for Graph Classification Extrapolations

Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimation

LARNet: Lie Algebra Residual Network for Face Recognition

Sinkhorn Label Allocation: Semi-Supervised Classification via Annealed Self-Training

Inferring Latent Dynamics Underlying Neural Population Activity via Neural Differential Equations

Private Adaptive Gradient Methods for Convex Optimization

Hierarchical Agglomerative Graph Clustering in Nearly-Linear Time

On Learnability via Gradient Method for Two-Layer ReLU Neural Networks in Teacher-Student Setting

LTL2Action: Generalizing LTL Instructions for Multi-Task RL

Learning Transferable Visual Models From Natural Language Supervision

Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement

Out-of-Distribution Generalization via Risk Extrapolation (REx)

TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models

Acceleration via Fractal Learning Rate Schedules

Local Correlation Clustering with Asymmetric Classification Errors

How and Why to Use Experimental Data to Evaluate Methods for Observational Causal Inference

Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity

The Impact of Record Linkage on Learning from Feature Partitioned Data

The Symmetry between Arms and Knapsacks: A Primal-Dual Approach for Bandits with Knapsacks

Robust Inference for High-Dimensional Linear Models via Residual Randomization

XOR-CD: Linearly Convergent Constrained Structure Generation

Just Train Twice: Improving Group Robustness without Training Group Information

Permutation Weighting

Deep kernel processes

Examining and Combating Spurious Features under Distribution Shift

Learning to Price Against a Moving Target

Bilinear Classes: A Structural Framework for Provable Generalization in RL

Emergent Social Learning via Multi-agent Reinforcement Learning

Improving Generalization in Meta-learning via Task Augmentation

Message Passing Adaptive Resonance Theory for Online Active Semi-supervised Learning

Batch Value-function Approximation with Only Realizability

Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework

Revisiting Rainbow: Promoting more insightful and inclusive deep reinforcement learning research

Instance Specific Approximations for Submodular Maximization

Learning Representations by Humans, for Humans

Accumulated Decoupled Learning with Gradient Staleness Mitigation for Convolutional Neural Networks

Voice2Series: Reprogramming Acoustic Models for Time Series Classification

Path Planning using Neural A* Search

CATE: Computation-aware Neural Architecture Encoding with Transformers

Unified Robust Semi-Supervised Variational Autoencoder

Outside the Echo Chamber: Optimizing the Performative Risk

Catformer: Designing Stable Transformers via Sensitivity Analysis

MOTS: Minimax Optimal Thompson Sampling

On the Power of Localized Perceptron for Label-Optimal Learning of Halfspaces with Adversarial Noise

Riemannian Convex Potential Maps

Debiasing a First-order Heuristic for Approximate Bi-level Optimization

Isometric Gaussian Process Latent Variable Model for Dissimilarity Data

Relative Positional Encoding for Transformers with Linear Complexity

GANMEX: One-vs-One Attributions using GAN-based Model Explainability

Defense against backdoor attacks via robust covariance estimation

Bayesian Attention Belief Networks

Nondeterminism and Instability in Neural Network Optimization

Large-Scale Multi-Agent Deep FBSDEs

Generative Adversarial Transformers

CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee

SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation

Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential Recommendation

Straight to the Gradient: Learning to Use Novel Tokens for Neural Text Generation

GMAC: A Distributional Perspective on Actor-Critic Framework

Order Matters: Probabilistic Modeling of Node Sequence for Graph Generation

Asynchronous Decentralized Optimization With Implicit Stochastic Variance Reduction

Learning Stochastic Behaviour from Aggregate Data

Scalable Computations of Wasserstein Barycenter via Input Convex Neural Networks

Is Space-Time Attention All You Need for Video Understanding?

Interaction-Grounded Learning

The Emergence of Individuality

Group-Sparse Matrix Factorization for Transfer Learning of Word Embeddings

Large-Scale Meta-Learning with Continual Trajectory Shifting

Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation

Sharf: Shape-conditioned Radiance Fields from a Single View

Commutative Lie Group VAE for Disentanglement Learning

A Receptor Skeleton for Capsule Neural Networks

On the price of explainability for some clustering problems

GRAND: Graph Neural Diffusion

Variance Reduced Training with Stratified Sampling for Forecasting Models

Quantitative Understanding of VAE as a Non-linearly Scaled Isometric Embedding

ProGraML: A Graph-based Program Representation for Data Flow Analysis and Compiler Optimizations

Selecting Data Augmentation for Simulating Interventions

On Explainability of Graph Neural Networks via Subgraph Explorations

Event Outlier Detection in Continuous Time

Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning

What Makes for End-to-End Object Detection?

Understanding Noise Injection in GANs

Learning by Turning: Neural Architecture Aware Optimisation

FILTRA: Rethinking Steerable CNN by Filter Transform

Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrix

Crystallization Learning with the Delaunay Triangulation

Principled Exploration via Optimistic Bootstrapping and Backward Induction

Near-Optimal Entrywise Anomaly Detection for Low-Rank Matrices with Sub-Exponential Noise

TFix: Learning to Fix Coding Errors with a Text-to-Text Transformer

Mind the Box: $l_1$-APGD for Sparse Adversarial Attacks on Image Classifiers

On the Problem of Underranking in Group-Fair Ranking

On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game

Improving Ultrametrics Embeddings Through Coresets

Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More

Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured Transitions

Efficient Online Learning for Dynamic k-Clustering

Federated Learning of User Verification Models Without Sharing Embeddings

Rethinking Neural vs. Matrix-Factorization Collaborative Filtering: the Theoretical Perspectives

Incentivized Bandit Learning with Self-Reinforcing User Preferences

Quantile Bandits for Best Arms Identification

Robust Reinforcement Learning using Least Squares Policy Iteration with Provable Performance Guarantees

STRODE: Stochastic Boundary Ordinary Differential Equation

Align, then memorise: the dynamics of learning with feedback alignment

Communication-Efficient Distributed SVD via Local Power Iterations

Breaking the Deadly Triad with a Target Network

Adversarial Robustness Guarantees for Random Deep Neural Networks

In-Database Regression in Input Sparsity Time

Inferring serial correlation with dynamic backgrounds

The Limits of Min-Max Optimization Algorithms: Convergence to Spurious Non-Critical Sets

Towards Defending against Adversarial Examples via Attack-Invariant Features

Asymptotic Normality and Confidence Intervals for Prediction Risk of the Min-Norm Least Squares Estimator

Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth

Communication-Efficient Distributed Optimization with Quantized Preconditioners

AdaXpert: Adapting Neural Architecture for Growing Data

On Reinforcement Learning with Adversarial Corruption and Its Application to Block MDP

SoundDet: Polyphonic Moving Sound Event Detection and Localization from Raw Waveform

On Characterizing GAN Convergence Through Proximal Duality Gap

Unbalanced minibatch Optimal Transport; applications to Domain Adaptation

What's in the Box? Exploring the Inner Life of Neural Networks with Robust Rules

Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed

ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases

Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient

Bootstrapping Fitted Q-Evaluation for Off-Policy Inference

Fast Algorithms for Stackelberg Prediction Game with Least Squares Loss

Phasic Policy Gradient

Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization

A Riemannian Block Coordinate Descent Method for Computing the Projection Robust Wasserstein Distance

Near-Optimal Representation Learning for Linear Bandits and Linear RL

How Framelets Enhance Graph Neural Networks

A Sampling-Based Method for Tensor Ring Decomposition

Necessary and sufficient conditions for causal feature selection in time series with latent common causes

Exponential Lower Bounds for Batch Reinforcement Learning: Batch RL can be Exponentially Harder than Online RL

Sawtooth Factorial Topic Embeddings Guided Gamma Belief Network