Search Schedule »

Show All »
July 17, 2022 Expo schedule » New in ML »

Timezone: America/New_York »

Indicates the beginning of a session

 Thu Jul 21, 2022

Time Hall E
06:00 PM (Posters)
Structure Preserving Neural Networks: A Case Study in the Entropy Closure of the Boltzmann Equation Hall E #100
Composing Partial Differential Equations with Physics-Aware Neural Networks Hall E #102
Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval Hall E #104
Towards Coherent and Consistent Use of Entities in Narrative Generation Hall E #106
Optimally Controllable Perceptual Lossy Compression Hall E #110
Learning to Solve PDE-constrained Inverse Problems with Graph Networks Hall E #112
ModLaNets: Learning Generalisable Dynamics via Modularity and Physical Inductive Bias Hall E #114
Learning to Estimate and Refine Fluid Motion with Physical Dynamics Hall E #116
Tractable Dendritic RNNs for Reconstructing Nonlinear Dynamical Systems Hall E #118
An Intriguing Property of Geophysics Inversion Hall E #120
Particle Transformer for Jet Tagging Hall E #122
BabelTower: Learning to Auto-parallelized Program Translation Hall E #124
ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers Hall E #126
On Distribution Shift in Learning-based Bug Detectors Hall E #128
A Context-Integrated Transformer-Based Neural Network for Auction Design Hall E #133
Domain Adaptation for Time Series Forecasting via Attention Sharing Hall E #131
Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations Hall E #129
Disentangling Disease-related Representation from Obscure for Disease Prediction Hall E #127
Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization Hall E #125
Blocks Assemble! Learning to Assemble with Large-Scale Structured Reinforcement Learning Hall E #123
Learning of Cluster-based Feature Importance for Electronic Health Record Time-series Hall E #121
Do Differentiable Simulators Give Better Policy Gradients? Hall E #119
Adaptive Conformal Predictions for Time Series Hall E #117
Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents Hall E #115
Rethinking Graph Neural Networks for Anomaly Detection Hall E #113
Fast Aquatic Swimmer Optimization with Differentiable Projective Dynamics and Neural Network Hydrodynamic Models Hall E #111
Proving Theorems using Incremental Learning and Hindsight Experience Replay Hall E #109
Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning Hall E #107
Neural Inverse Kinematic Hall E #105
GLaM: Efficient Scaling of Language Models with Mixture-of-Experts Hall E #208
Deploying Convolutional Networks on Untrusted Platforms Using 2D Holographic Reduced Representations Hall E #210
Object Permanence Emerges in a Random Walk along Memory Hall E #212
Flow-Guided Sparse Transformer for Video Deblurring Hall E #214
N-Penetrate: Active Learning of Neural Collision Handler for Complex 3D Mesh Deformations Hall E #216
Staged Training for Transformer Language Models Hall E #218
Near-Exact Recovery for Tomographic Inverse Problems via Deep Learning Hall E #220
Self-supervised learning with random-projection quantizer for speech recognition Hall E #222
Learning Multiscale Transformer Models for Sequence Generation Hall E #224
NP-Match: When Neural Processes meet Semi-Supervised Learning Hall E #226
Revisiting End-to-End Speech-to-Text Translation From Scratch Hall E #228
Data Scaling Laws in NMT: The Effect of Noise and Architecture Hall E #230
Dialog Inpainting: Turning Documents into Dialogs Hall E #232
Does the Data Induce Capacity Control in Deep Learning? Hall E #234
Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming Hall E #236
Memory-Based Model Editing at Scale Hall E #237
Winning the Lottery Ahead of Time: Efficient Early Network Pruning Hall E #235
Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets Hall E #233
AutoSNN: Towards Energy-Efficient Spiking Neural Networks Hall E #229
Overcoming Oscillations in Quantization-Aware Training Hall E #227
Dataset Condensation via Efficient Synthetic-Data Parameterization Hall E #225
Searching for BurgerFormer with Micro-Meso-Macro Space Design Hall E #223
Multi-scale Feature Learning Dynamics: Insights for Double Descent Hall E #221
Dataset Condensation with Contrastive Signals Hall E #219
Equivariant Priors for compressed sensing with unknown orientation Hall E #217
Injecting Logical Constraints into Neural Networks via Straight-Through Estimators Hall E #215
Prioritized Training on Points that are Learnable, Worth Learning, and not yet Learnt Hall E #213
A Neural Tangent Kernel Perspective of GANs Hall E #211
Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models Hall E #209
Neural Inverse Transform Sampler Hall E #207
Antibody-Antigen Docking and Design via Hierarchical Structure Refinement Hall E #205
Diffusion Models for Adversarial Purification Hall E #203
Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification Hall E #201
VarScene: A Deep Generative Model for Realistic Scene Graph Synthesis Hall E #300
It’s Raw! Audio Generation with State-Space Models Hall E #302
Unsupervised Image Representation Learning with Deep Latent Particles Hall E #304
Learning Efficient and Robust Ordinary Differential Equations via Invertible Neural Networks Hall E #306
Neuro-Symbolic Hierarchical Rule Induction Hall E #308
General-purpose, long-context autoregressive modeling with Perceiver AR Hall E #310
Marginal Tail-Adaptive Normalizing Flows Hall E #312
SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks Hall E #314
NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance Fields Hall E #316
Equivariance versus Augmentation for Spherical Images Hall E #318
Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training Hall E #320
Neural Network Poisson Models for Behavioural and Neural Spike Train Data Hall E #322
A Branch and Bound Framework for Stronger Adversarial Attacks of ReLU Networks Hall E #324
GACT: Activation Compressed Training for Generic Network Architectures Hall E #326
Fast Finite Width Neural Tangent Kernel Hall E #328
G-Mixup: Graph Data Augmentation for Graph Classification Hall E #330
Universal Hopfield Networks: A General Framework for Single-Shot Associative Memory Models Hall E #332
Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts Hall E #334
Continual Learning with Guarantees via Weight Interval Constraints Hall E #336
Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness Hall E #338
Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities Hall E #337
Comprehensive Analysis of Negative Sampling in Knowledge Graph Representation Learning Hall E #335
Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness Hall E #333
Adversarial Masking for Self-Supervised Learning Hall E #331
Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Performance Hall E #329
Multirate Training of Neural Networks Hall E #325
Variational Wasserstein gradient flow Hall E #323
Building Robust Ensembles via Margin Boosting Hall E #321
Investigating Generalization by Controlling Normalized Margin Hall E #319
Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation Hall E #317
VLUE: A Multi-Task Multi-Dimension Benchmark for Evaluating Vision-Language Pre-training Hall E #315
Let Invariant Rationale Discovery Inspire Graph Contrastive Learning Hall E #313
Graph Neural Architecture Search Under Distribution Shifts Hall E #311
How Powerful are Spectral Graph Neural Networks Hall E #309
Constraint-based graph network simulator Hall E #307
PACE: A Parallelizable Computation Encoder for Directed Acyclic Graphs Hall E #305
Structure-Aware Transformer for Graph Representation Learning Hall E #303
Ripple Attention for Visual Perception with Sub-quadratic Complexity Hall E #301
Self-supervised Models are Good Teaching Assistants for Vision Transformers Hall E #400
Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations Hall E #402
In defense of dual-encoders for neural ranking Hall E #404
From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked Transformers Hall E #406
Linear Complexity Randomized Self-attention Mechanism Hall E #408
Efficient Representation Learning via Adaptive Context Pooling Hall E #410
Toward Compositional Generalization in Object-Oriented World Modeling Hall E #412
Fast Population-Based Reinforcement Learning on a Single Machine Hall E #414
NeuralEF: Deconstructing Kernels by Deep Neural Networks Hall E #416
Visual Attention Emerges from Recurrent Sparse Reconstruction Hall E #418
Transformer Quality in Linear Time Hall E #420
What Dense Graph Do You Need for Self-Attention? Hall E #422
Dual Decomposition of Convex Optimization Layers for Consistent Attention in Medical Images Hall E #424
Multi Resolution Analysis (MRA) for Approximate Self-Attention Hall E #426
Dynamic Topic Models for Temporal Document Networks Hall E #428
A Functional Information Perspective on Model Interpretation Hall E #432
Be Like Water: Adaptive Floating Point for Machine Learning Hall E #434
Lie Point Symmetry Data Augmentation for Neural PDE Solvers Hall E #436
Bregman Neural Networks Hall E #438
Quantifying and Learning Linear Symmetry-Based Disentanglement Hall E #439
Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups Hall E #437
PDO-s3DCNNs: Partial Differential Operator Based Steerable 3D CNNs Hall E #435
Utilizing Expert Features for Contrastive Learning of Time-Series Representations Hall E #433
(Non-)Convergence Results for Predictive Coding Networks Hall E #431
Representation Topology Divergence: A Method for Comparing Neural Network Representations. Hall E #429
Measuring Representational Robustness of Neural Networks Through Shared Invariances Hall E #427
The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention Hall E #425
Flowformer: Linearizing Transformers with Conservation Flows Hall E #423
Spatial-Channel Token Distillation for Vision MLPs Hall E #421
Neurocoder: General-Purpose Computation Using Stored Neural Programs Hall E #419
Improving Transformers with Probabilistic Attention Keys Hall E #417
Rethinking Attention-Model Explainability through Faithfulness Violation Test Hall E #415
AGNAS: Attention-Guided Micro- and Macro-Architecture Search Hall E #413
Convergence of Invariant Graph Networks Hall E #411
Rich Feature Construction for the Optimization-Generalization Dilemma Hall E #409
NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework Hall E #407
Resilient and Communication Efficient Learning for Heterogeneous Federated Systems Hall E #405
Augment with Care: Contrastive Learning for Combinatorial Problems Hall E #403
Cycle Representation Learning for Inductive Relation Prediction Hall E #401
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time Hall E #500
Do More Negative Samples Necessarily Hurt In Contrastive Learning? Hall E #502
MetAug: Contrastive Learning via Meta Feature Augmentation Hall E #504
Investigating Why Contrastive Learning Benefits Robustness against Label Noise Hall E #506
Contrastive Learning with Boosted Memorization Hall E #508
Identity-Disentangled Adversarial Augmentation for Self-supervised Learning Hall E #510
Interventional Contrastive Learning with Meta Semantic Regularizer Hall E #512
On the Surrogate Gap between Contrastive and Supervised Losses Hall E #514
Exploring the Gap between Collapsed & Whitened Features in Self-Supervised Learning Hall E #516
Locally Sparse Neural Networks for Tabular Biomedical Data Hall E #518
Dual Perspective of Label-Specific Feature Learning for Multi-Label Classification Hall E #520
Detecting Corrupted Labels Without Training a Model to Predict Hall E #522
Prototype-Anchored Learning for Learning with Imperfect Annotations Hall E #524
Learning to Predict Graphs with Fused Gromov-Wasserstein Barycenters Hall E #526
Deep Safe Incomplete Multi-view Clustering: Theorem and Algorithm Hall E #528
Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network Hall E #530
Invariant Ancestry Search Hall E #532
Unaligned Supervision for Automatic Music Transcription in The Wild Hall E #534
Fourier Learning with Cyclical Data Hall E #536
Linear Adversarial Concept Erasure Hall E #538
Score Matching Enables Causal Discovery of Nonlinear Additive Noise Models Hall E #539
Provable Domain Generalization via Invariant-Feature Subspace Recovery Hall E #537
Subspace Learning for Effective Meta-Learning Hall E #535
Continual Learning via Sequential Function-Space Variational Inference Hall E #533
Efficient Test-Time Model Adaptation without Forgetting Hall E #529
A Hierarchical Transitive-Aligned Graph Kernel for Un-attributed Graphs Hall E #527
Leverage Score Sampling for Tensor Product Matrices in Input Sparsity Time Hall E #525
Random Gegenbauer Features for Scalable Kernel Methods Hall E #523
Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptile Hall E #521
Functional Output Regression with Infimal Convolution: Exploring the Huber and $\epsilon$-insensitive Losses Hall E #519
Measuring dissimilarity with diffeomorphism invariance Hall E #517
Importance Weighted Kernel Bayes' Rule Hall E #515
An Asymptotic Test for Conditional Independence using Analytic Kernel Embeddings Hall E #513
Nyström Kernel Mean Embeddings Hall E #511
Distribution Regression with Sliced Wasserstein Kernels Hall E #509
Learning Stable Classifiers by Transferring Unstable Features Hall E #507
Data-Efficient Double-Win Lottery Tickets from Robust Pre-training Hall E #505
Attentional Meta-learners for Few-shot Polythetic Classification Hall E #503
C*-algebra Net: A New Approach Generalizing Neural Network Parameters to C*-algebra Hall E #501
Nonlinear Feature Diffusion on Hypergraphs Hall E #600
Robust Task Representations for Offline Meta-Reinforcement Learning via Contrastive Learning Hall E #604
Fast Provably Robust Decision Trees and Boosting Hall E #606
Order Constraints in Optimal Transport Hall E #608
Sublinear-Time Clustering Oracle for Signed Graphs Hall E #610
PAC-Bayesian Bounds on Rate-Efficient Classifiers Hall E #612
More Efficient Sampling for Tensor Decomposition With Worst-Case Guarantees Hall E #614
Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning Hall E #616
On the Convergence of Local Stochastic Compositional Gradient Descent with Momentum Hall E #618
SPDY: Accurate Pruning with Speedup Guarantees Hall E #620
Flashlight: Enabling Innovation in Tools for Machine Learning Hall E #622
On the Robustness of CountSketch to Adaptive Inputs Hall E #624
Fast-Rate PAC-Bayesian Generalization Bounds for Meta-Learning Hall E #626
Wide Neural Networks Forget Less Catastrophically Hall E #628
A Unified View on PAC-Bayes Bounds for Meta-Learning Hall E #630
MAML and ANIL Provably Learn Representations Hall E #632
C-MinHash: Improving Minwise Hashing with Circulant Permutation Hall E #634
Proximal Denoiser for Convergent Plug-and-Play Optimization with Nonconvex Regularization Hall E #636
Safe Exploration for Efficient Policy Evaluation and Comparison Hall E #638
Adversarial Attacks on Gaussian Process Bandits Hall E #639
GALAXY: Graph-based Active Learning at the Extreme Hall E #637
When Are Linear Stochastic Bandits Attackable? Hall E #635
UniRank: Unimodal Bandit Algorithms for Online Ranking Hall E #633
Correlation Clustering via Strong Triadic Closure Labeling: Fast Approximation Algorithms and Practical Lower Bounds Hall E #631
Interactive Correlation Clustering with Existential Cluster Constraints Hall E #629
Simultaneous Graph Signal Clustering and Graph Learning Hall E #627
Bregman Power k-Means for Clustering Exponential Family Data Hall E #625
SpaceMAP: Visualizing High-Dimensional Data by Space Expansion Hall E #623
Unsupervised Ground Metric Learning Using Wasserstein Singular Vectors Hall E #621
Understanding Doubly Stochastic Clustering Hall E #619
Faster Fundamental Graph Algorithms via Learned Predictions Hall E #617
Practical Almost-Linear-Time Approximation Algorithms for Hybrid and Overlapping Graph Clustering Hall E #615
Fair and Fast k-Center Clustering for Data Summarization Hall E #613
Online and Consistent Correlation Clustering Hall E #611
Generalized Leverage Scores: Geometric Interpretation and Applications Hall E #609
Adapting k-means Algorithms for Outliers Hall E #607
Accelerated, Optimal and Parallel: Some results on model-based stochastic optimization Hall E #605
Online Algorithms with Multiple Predictions Hall E #603
Parsimonious Learning-Augmented Caching Hall E #601
RUMs from Head-to-Head Contests Hall E #700
Quant-BnB: A Scalable Branch-and-Bound Method for Optimal Decision Trees with Continuous Features Hall E #702
Robustness in Multi-Objective Submodular Optimization: a Quantile Approach Hall E #704
Streaming Algorithm for Monotone k-Submodular Maximization with Cardinality Constraints Hall E #706
Adaptive Accelerated (Extra-)Gradient Methods with Variance Reduction Hall E #708
Adaptive Second Order Coresets for Data-efficient Machine Learning Hall E #710
Nesterov Accelerated Shuffling Gradient Method for Convex Optimization Hall E #712
Efficient Low Rank Convex Bounds for Pairwise Discrete Graphical Models Hall E #714
Deletion Robust Submodular Maximization over Matroids Hall E #716
The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks Hall E #718
Instance Dependent Regret Analysis of Kernelized Bandits Hall E #720
Proximal and Federated Random Reshuffling Hall E #722
Federated Learning with Partial Model Personalization Hall E #724
A Stochastic Multi-Rate Control Framework For Modeling Distributed Optimization Algorithms Hall E #726
Tackling Data Heterogeneity: A New Unified Framework for Decentralized SGD with Sample-induced Topology Hall E #728
Iterative Double Sketching for Faster Least-Squares Optimization Hall E #732
Learning to Cut by Looking Ahead: Cutting Plane Selection via Imitation Learning Hall E #734
A Regret Minimization Approach to Multi-Agent Control Hall E #736
Decision-Focused Learning: Through the Lens of Learning to Rank Hall E #739
Lightweight Projective Derivative Codes for Compressed Asynchronous Gradient Descent Hall E #737
Least Squares Estimation using Sketched Data with Heteroskedastic Errors Hall E #733
Debiaser Beware: Pitfalls of Centering Regularized Transport Maps Hall E #731
Bregman Proximal Langevin Monte Carlo via Bregman--Moreau Envelopes Hall E #729
Active Nearest Neighbor Regression Through Delaunay Refinement Hall E #727
A Convergence Theory for SVGD in the Population Limit under Talagrand's Inequality T1 Hall E #725
ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training Hall E #723
Federated Learning with Label Distribution Skew via Logits Calibration Hall E #721
Adaptive Random Walk Gradient Descent for Decentralized Optimization Hall E #719
POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging Hall E #717
Secure Distributed Training at Scale Hall E #715
ASAP.SGD: Instance-based Adaptiveness to Staleness in Asynchronous SGD Hall E #713
Anarchic Federated Learning Hall E #711
Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learning Hall E #709
Global Optimization Networks Hall E #707
Generalized Federated Learning via Sharpness Aware Minimization Hall E #705
Delay-Adaptive Step-sizes for Asynchronous Learning Hall E #703
FedScale: Benchmarking Model and System Performance of Federated Learning at Scale Hall E #701
Learning Augmented Binary Search Trees Hall E #800
Communication-efficient Distributed Learning for Large Batch Optimization Hall E #802
Born-Infeld (BI) for AI: Energy-Conserving Descent (ECD) for Optimization Hall E #804
An Exact Symbolic Reduction of Linear Smart Predict+Optimize to Mixed Integer Linear Programming Hall E #808
Multi-Level Branched Regularization for Federated Learning Hall E #810
Gaussian Process Uniform Error Bounds with Unknown Hyperparameters for Safety-Critical Applications Hall E #812
Input Dependent Sparse Gaussian Processes Hall E #814
AutoIP: A United Framework to Integrate Physics into Gaussian Processes Hall E #816
Stochastic Deep Networks with Linear Competing Units for Model-Agnostic Meta-Learning Hall E #818
Nonparametric Factor Trajectory Learning for Dynamic Tensor Decomposition Hall E #820
Nonparametric Embeddings of Sparse High-Order Interaction Events Hall E #822
Adapting the Linearised Laplace Model Evidence for Modern Deep Learning Hall E #824
NOMU: Neural Optimization-based Model Uncertainty Hall E #826
Bayesian Model Selection, the Marginal Likelihood, and Generalization Hall E #828
Scaling Structured Inference with Randomization Hall E #832
Discrete Tree Flows via Tree-Structured Permutations Hall E #834
Calibrated and Sharp Uncertainties in Deep Learning via Density Estimation Hall E #836
The Importance of Non-Markovianity in Maximum State Entropy Exploration Hall E #838
Continuous Control with Action Quantization from Demonstrations Hall E #837
Plan Your Target and Learn Your Skills: Transferable State-Only Imitation Learning via Decoupled Policy Optimization Hall E #835
Inverse Contextual Bandits: Learning How Behavior Evolves over Time Hall E #833
Balancing Sample Efficiency and Suboptimality in Inverse Reinforcement Learning Hall E #829
Towards Uniformly Superhuman Autonomy via Subdominance Minimization Hall E #827
Causal Imitation Learning under Temporally Correlated Noise Hall E #825
Interactive Inverse Reinforcement Learning for Cooperative Games Hall E #823
A Hierarchical Bayesian Approach to Inverse Reinforcement Learning with Symbolic Reward Machines Hall E #821
Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations Hall E #817
Learning from Demonstration: Provably Efficient Adversarial Policy Imitation with Linear Function Approximation Hall E #815
The Unsurprising Effectiveness of Pre-Trained Vision Models for Control Hall E #813
COLA: Consistent Learning with Opponent-Learning Awareness Hall E #811
A Self-Play Posterior Sampling Algorithm for Zero-Sum Markov Games Hall E #809
A Framework for Learning to Request Rich and Contextually Useful Information from Humans Hall E #807
Learning Stochastic Shortest Path with Linear Function Approximation Hall E #805
Difference Advantage Estimation for Multi-Agent Policy Gradients Hall E #803
Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification Hall E #801
Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets Hall E #900
Learning Bellman Complete Representations for Offline Policy Evaluation Hall E #902
Doubly Robust Distributionally Robust Off-Policy Evaluation and Learning Hall E #904
A Simple Reward-free Approach to Constrained Reinforcement Learning Hall E #906
Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching Hall E #908
Temporal Difference Learning for Model Predictive Control Hall E #910
Model Selection in Batch Policy Optimization Hall E #912
Adversarially Trained Actor Critic for Offline Reinforcement Learning Hall E #914
Optimal Estimation of Policy Gradient via Double Fitted Iteration Hall E #916
Provably Efficient Offline Reinforcement Learning for Partially Observable Markov Decision Processes Hall E #918
Off-Policy Fitted Q-Evaluation with Differentiable Function Approximators: Z-Estimation and Inference Theory Hall E #920
Lagrangian Method for Q-Function Learning (with Applications to Machine Translation) Hall E #922
On the Role of Discount Factor in Offline Reinforcement Learning Hall E #924
EAT-C: Environment-Adversarial sub-Task Curriculum for Efficient Reinforcement Learning Hall E #926
Tell me why! Explanations support learning relational and causal structure Hall E #928
Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics Hall E #930
Generalised Policy Improvement with Geometric Policy Composition Hall E #932
Offline Meta-Reinforcement Learning with Online Self-Supervision Hall E #934
Divergence-Regularized Multi-Agent Actor-Critic Hall E #936
Understanding Policy Gradient Algorithms: A Sensitivity-Based Approach Hall E #929
Off-Policy Reinforcement Learning with Delayed Rewards Hall E #927
Direct Behavior Specification via Constrained Reinforcement Learning Hall E #923
Large Batch Experience Replay Hall E #921
Evolving Curricula with Regret-Based Environment Design Hall E #919
Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum Hall E #915
Transformers are Meta-Reinforcement Learners Hall E #913
Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks Hall E #911
Constrained Variational Policy Optimization for Safe Reinforcement Learning Hall E #909
On the Hidden Biases of Policy Mirror Ascent in Continuous Action Spaces Hall E #907
Asking for Knowledge (AFK): Training RL Agents to Query External Knowledge Using Language Hall E #905
Addressing Optimism Bias in Sequence Modeling for Reinforcement Learning Hall E #903
An Analytical Update Rule for General Policy Optimization Hall E #1002
Making Linear MDPs Practical via Contrastive Representation Learning Hall E #1004
Flow-based Recurrent Belief State Learning for POMDPs Hall E #1006
A Parametric Class of Approximate Gradient Updates for Policy Optimization Hall E #1008
Retrieval-Augmented Reinforcement Learning Hall E #1010
Robust Policy Learning over Multiple Uncertainty Sets Hall E #1012
Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RL Hall E #1014
Learning Dynamics and Generalization in Deep Reinforcement Learning Hall E #1018
From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses Hall E #1020
Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error Hall E #1022
EqR: Equivariant Representations for Data-Efficient Reinforcement Learning Hall E #1026
Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning Environments Hall E #1027
Off-Policy Evaluation for Large Action Spaces via Embeddings Hall E #1025
Online Decision Transformer Hall E #1023
Learning-based Optimisation of Particle Accelerators Under Partial Observability Without Real-World Training Hall E #1021
How to Leverage Unlabeled Data in Offline Reinforcement Learning Hall E #1019
Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning Hall E #1017
A Psychological Theory of Explainability Hall E #1015
Task-aware Privacy Preservation for Multi-dimensional Data Hall E #1013
Strategic Representation Hall E #1011
Causal Conceptions of Fairness and their Consequences Hall E #1009
Fairness with Adaptive Weights Hall E #1007
Understanding Instance-Level Impact of Fairness Constraints Hall E #1001
Achieving Fairness at No Utility Cost via Data Reweighing with Influence Hall E #1003
Mitigating Gender Bias in Face Recognition using the von Mises-Fisher Mixture Model Hall E #1106
Selective Regression under Fairness Criteria Hall E #1108
Input-agnostic Certified Group Fairness via Gaussian Parameter Smoothing Hall E #1110
Generalized Strategic Classification and the Case of Aligned Incentives Hall E #1112
Improving Screening Processes via Calibrated Subset Selection Hall E #1114
On the Convergence of the Shapley Value in Parametric Bayesian Learning Games Hall E #1116
Data-SUITE: Data-centric identification of in-distribution incongruous examples Hall E #1118
Counterfactual Prediction for Outcome-Oriented Treatments Hall E #1120
Optimal Algorithms for Mean Estimation under Local Differential Privacy Hall E #1122
First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach Hall E #1124
Generic Coreset for Scalable Learning of Monotonic Kernels: Logistic Regression, Sigmoid and more Hall E #1126
Shuffle Private Linear Contextual Bandits Hall E #1125
Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity Hall E #1123
Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes Hall E #1121
Label Ranking through Nonparametric Regression Hall E #1119
Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost Hall E #1117
A Simple Unified Framework for High Dimensional Bandit Problems Hall E #1115
A Reduction from Linear Contextual Bandits Lower Bounds to Estimations Lower Bounds Hall E #1113
Branching Reinforcement Learning Hall E #1111
Fast rates for noisy interpolation require rethinking the effect of inductive bias Hall E #1109
Near-Optimal Algorithms for Autonomous Exploration and Multi-Goal Stochastic Shortest Path Hall E #1107
Federated Reinforcement Learning: Linear Speedup Under Markovian Sampling Hall E #1101
Entropic Gromov-Wasserstein between Gaussian Distributions Hall E #1103
No-Regret Learning in Partially-Informed Auctions Hall E #1206
On Last-Iterate Convergence Beyond Zero-Sum Games Hall E #1208
Kernelized Multiplicative Weights for 0/1-Polyhedral Games: Bridging the Gap Between Learning in Extensive-Form and Normal-Form Games Hall E #1210
Fictitious Play and Best-Response Dynamics in Identical Interest and Zero-Sum Stochastic Games Hall E #1212
On the Convergence of Inexact Predictor-Corrector Methods for Linear Programming Hall E #1214
Nested Bandits Hall E #1216
Information Discrepancy in Strategic Learning Hall E #1218
UnderGrad: A Universal Black-Box Optimization Method with Almost Dimension-Free Convergence Rate Guarantees Hall E #1220
Safe Learning in Tree-Form Sequential Decision Making: Handling Hard and Soft Constraints Hall E #1222
A Marriage between Adversarial Team Games and 2-player Games: Enabling Abstractions, No-regret Learning, and Subgame Solving Hall E #1224
Exact Learning of Preference Structure: Single-peaked Preferences and Beyond Hall E #1221
Selling Data To a Machine Learner: Pricing via Costly Signaling Hall E #1219
Hardness and Algorithms for Robust and Sparse Optimization Hall E #1217
A Convergent and Dimension-Independent Min-Max Optimization Algorithm Hall E #1215
Stochastic Continuous Submodular Maximization: Boosting via Non-oblivious Function Hall E #1213
Accelerated Gradient Methods for Geodesically Convex Optimization: Tractable Algorithms and Convergence Analysis Hall E #1211
The Complexity of k-Means Clustering when Little is Known Hall E #1207
Iterative Hard Thresholding with Adaptive Regularization: Sparser Solutions Without Sacrificing Runtime Hall E #1209
3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation Hall E #1310
Nearly Optimal Catoni’s M-estimator for Infinite Variance Hall E #1312
Strategies for Safe Multi-Armed Bandits with Logarithmic Regret and Risk Hall E #1314
Local Linear Convergence of Douglas-Rachford for Linear Programming: a Probabilistic Analysis Hall E #1316
Contextual Information-Directed Sampling Hall E #1318
Breaking the $\sqrt{T}$ Barrier: Instance-Independent Logarithmic Regret in Stochastic Contextual Linear Bandits Hall E #1320
Universal and data-adaptive algorithms for model selection in linear contextual bandits Hall E #1319
Regret Minimization with Performative Feedback Hall E #1317
A Simple yet Universal Strategy for Online Convex Optimization Hall E #1315
Deep Hierarchy in Bandits Hall E #1309
Distributionally-Aware Kernelized Bandit Problems for Risk Aversion Hall E #1311
Asymptotically-Optimal Gaussian Bandits with Side Observations Hall E #1409
Learning from a Learning User for Optimal Recommendations Hall E #1414
Thresholded Lasso Bandit Hall E #1416
Versatile Dueling Bandits: Best-of-both World Analyses for Learning from Relative Preferences Hall E #1418
Decentralized Online Convex Optimization in Networked Systems Hall E #1411
Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning approach Hall E #1413
Sketching Algorithms and Lower Bounds for Ridge Regression Hall E #1420
On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning Hall E #1422
Utility Theory for Sequential Decision Making Hall E #1424
Online Learning with Knapsacks: the Best of Both Worlds Hall E #1426
Optimal Clustering with Noisy Queries via Multi-Armed Bandit Hall E #1428