Filter Events:

SUN 18 JUL

5 a.m.

Expo Talk Panel:

Machine Learning for Addressing Power Grid Congestion

(ends 6:00 AM)

Expo Workshop:

Real World RL: Azure Personalizer & Vowpal Wabbit

(ends 9:30 AM)

Expo Workshop:

High-Quality Data Labeling at Scale with Toloka

(ends 9:00 AM)

6 a.m.

Expo Talk Panel:

The latest advances and use-cases in the field of Causal AI

(ends 7:00 AM)

7 a.m.

Expo Talk Panel:

Unique Research Opportunities in AI Algorithms, Health, Traffic, and Weather

(ends 8:00 AM)

8 a.m.

Expo Talk Panel:

Cool Moves: Decoupling physical motions and self-avatar motions in Virtual Reality

(ends 9:00 AM)

9 a.m.

Expo Demonstration:

Neural Video Codec Demo

(ends 10:00 AM)

10 a.m.

Expo Talk Panel:

IBM Analog Hardware Acceleration Kit

(ends 11:00 AM)

5 p.m.

Expo Talk Panel:

Enterprise-Strength Federated Learning: New Algorithms, New Paradigms, and a Participant-Interactive Demonstration Session

(ends 5:59 PM)

Expo Workshop:

PaddlePaddle-based Deep Learning at Baidu

(ends 9:00 PM)

7 p.m.

Expo Talk Panel:

Graviti Open Datasets: A peek into the future of Open Data

(ends 8:00 PM)

9 p.m.

Expo Demonstration:

Explainable Entity Matching for Master Data Management

(ends 10:00 PM)

MON 19 JUL

6 a.m.

8 a.m.

Tutorial:

Continual Learning with Deep Architectures

(ends 11:05 AM)

Tutorial:

From ML research to ML products: A path towards building models with real-world impact

(ends 11:15 AM)

Tutorial:

Natural-XAI: Explainable AI with Natural Language Explanations

(ends 11:00 AM)

Tutorial:

Responsible AI in Industry: Practical Challenges and Lessons Learned

(ends 11:00 AM)

Tutorial:

Sparsity in Deep Learning: Pruning and growth for efficient inference and training

(ends 10:59 AM)

Tutorial:

Synthetic Healthcare Data Generation and Assessment: Challenges, Methods, and Impact on Machine Learning

(ends 11:00 AM)

Affinity Workshop:

LatinX in AI (LXAI) Research at ICML 2021

(ends 5:00 PM)

noon

Tutorial:

Online and non-stochastic control

(ends 3:00 PM)

Tutorial:

Random Matrix Theory and ML (RMT+ML)

(ends 3:00 PM)

Tutorial:

Unsupervised Learning for Reinforcement Learning

(ends 3:00 PM)

Tutorial:

Social Implications of Large Language Models

(ends 2:50 PM)

5 p.m.

6 p.m.

Affinity Poster Session:

LatinX in AI, Queer in AI, WiML - Joint Poster Session

(ends 8:00 PM)

8 p.m.

Tutorial:

Privacy in learning: Basics and the interplay

(ends 11:00 PM)

Tutorial:

Self-Attention for Computer Vision

(ends 10:45 PM)

TUE 20 JUL

5 a.m.

Optimal Transport [5:00-6:00]

Oral s 5:00-5:20

[5:00] Scalable Computations of Wasserstein Barycenter via Input Convex Neural Networks

Spotlight s 5:20-5:50

[5:20] Outlier-Robust Optimal Transport

[5:25] Dataset Dynamics via Gradient Flows in Probability Space

[5:30] Sliced Iterative Normalizing Flows

[5:35] Low-Rank Sinkhorn Factorization

[5:40] Unbalanced minibatch Optimal Transport; applications to Domain Adaptation

[5:45] Making transport more robust and interpretable by moving data through a small number of anchor points

Q&A s 5:50-5:55

[5:50] Q&A

(ends 6:00 AM)

Deep Learning Applications [5:00-6:00]

Oral s 5:00-5:20

[5:00] Attention is not all you need: pure attention loses rank doubly exponentially with depth

Spotlight s 5:20-5:50

[5:20] Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation

[5:25] Efficient Generative Modelling of Protein Structure Fragments using a Deep Markov Model

[5:30] Exploiting structured data for learning contagious diseases under incomplete testing

[5:35] Strategic Classification Made Practical

[5:40] Large-Margin Contrastive Learning with Distance Polarization Regularizer

[5:45] SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation

Q&A s 5:50-5:55

[5:50] Q&A

(ends 6:00 AM)

Deep Reinforcement Learning 1 [5:00-6:00]

Oral s 5:00-5:20

[5:00] Phasic Policy Gradient

Spotlight s 5:20-5:50

[5:20] Reinforcement Learning with Prototypical Representations

[5:25] Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Exploration

[5:30] Muesli: Combining Improvements in Policy Optimization

[5:35] Unsupervised Learning of Visual 3D Keypoints for Control

[5:40] Learning Task Informed Abstractions

[5:45] State Entropy Maximization with Random Encoders for Efficient Exploration

Q&A s 5:50-5:55

[5:50] Q&A

(ends 6:00 AM)

Auto-ML and Optimization [5:00-6:00]

Oral s 5:00-5:20

[5:00] BORE: Bayesian Optimization by Density-Ratio Estimation

Spotlight s 5:20-5:45

[5:20] AutoSampling: Search for Effective Data Sampling Schedules

[5:25] HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search

[5:30] Bias-Robust Bayesian Optimization via Dueling Bandits

[5:35] Zeroth-Order Non-Convex Learning via Hierarchical Dual Averaging

[5:40] Sparsifying Networks via Subdifferential Inclusion

Q&A s 5:45-5:50

[5:45] Q&A

(ends 6:00 AM)

Reinforcement Learning (Multi-agent) [5:00-6:00]

Oral s 5:00-5:20

[5:00] Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot

Spotlight s 5:20-5:45

[5:20] UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning

[5:25] A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning

[5:30] Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solvers

[5:35] PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration

[5:40] Imitation by Predicting Observations

Q&A s 5:45-5:50

[5:45] Q&A

(ends 6:00 AM)

Deep Learning Architectures [5:00-6:00]

Oral s 5:00-5:20

[5:00] Relative Positional Encoding for Transformers with Linear Complexity

Spotlight s 5:20-5:50

[5:20] A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibration

[5:25] A Unified Lottery Ticket Hypothesis for Graph Neural Networks

[5:30] Generative Adversarial Transformers

[5:35] Evolving Attention with Residual Convolutions

[5:40] Zoo-Tuning: Adaptive Transfer from A Zoo of Models

[5:45] UnICORNN: A recurrent model for learning very long time dependencies

Q&A s 5:50-5:55

[5:50] Q&A

(ends 6:00 AM)

Graph Learning [5:00-6:00]

Oral s 5:00-5:20

[5:00] Size-Invariant Graph Representations for Graph Classification Extrapolations

Spotlight s 5:20-5:50

[5:20] Consistent Nonparametric Methods for Network Assisted Covariate Estimation

[5:25] Explainable Automated Graph Representation Learning with Hyperparameter Importance

[5:30] Breaking the Limits of Message Passing Graph Neural Networks

[5:35] From Local Structures to Size Generalization in Graph Neural Networks

[5:40] Interpretable Stability Bounds for Spectral Graph Filters

[5:45] Learning Node Representations Using Stationary Flow Prediction on Large Payment and Cash Transaction Networks

Q&A s 5:50-5:55

[5:50] Q&A

(ends 6:00 AM)

Deep Reinforcement Learning 2 [5:00-6:00]

Oral s 5:00-5:20

[5:00] Deeply-Debiased Off-Policy Interval Estimation

Spotlight s 5:20-5:45

[5:20] Offline Contextual Bandits with Overparameterized Models

[5:25] Demonstration-Conditioned Reinforcement Learning for Few-Shot Imitation

[5:30] A New Representation of Successor Features for Transfer across Dissimilar Environments

[5:35] Preferential Temporal Difference Learning

[5:40] On the Optimality of Batch Policy Optimization Algorithms

Q&A s 5:45-5:50

[5:45] Q&A

(ends 6:00 AM)

Optimization (Distributed) [5:00-6:00]

Oral s 5:00-5:20

[5:00] Optimal Complexity in Decentralized Training

Spotlight s 5:20-5:50

[5:20] Stochastic Sign Descent Methods: New Algorithms and Better Theory

[5:25] Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning

[5:30] A Hybrid Variance-Reduced Method for Decentralized Stochastic Non-Convex Optimization

[5:35] Asynchronous Decentralized Optimization With Implicit Stochastic Variance Reduction

[5:40] Newton Method over Networks is Fast up to the Statistical Precision

[5:45] Federated Learning under Arbitrary Communication Patterns

Q&A s 5:50-5:55

[5:50] Q&A

(ends 6:00 AM)

6 a.m.

Deep Learning (Bayesian) [6:00-7:00]

Oral s 6:00-6:20

[6:00] What Are Bayesian Neural Network Posteriors Really Like?

Spotlight s 6:20-6:50

[6:20] Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning

[6:25] Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty Estimation

[6:30] Deep kernel processes

[6:35] Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processes

[6:40] Bayesian Deep Learning via Subnetwork Inference

[6:45] Generative Particle Variational Inference via Estimation of Functional Gradients

Q&A s 6:50-6:55

[6:50] Q&A

(ends 7:00 AM)

Deep Learning Theory 1 [6:00-7:00]

Oral s 6:00-6:20

[6:00] Let's Agree to Degree: Comparing Graph Convolutional Networks in the Message-Passing Framework

Spotlight s 6:20-6:50

[6:20] Fundamental Tradeoffs in Distributionally Adversarial Training

[6:25] Towards Understanding Learning in Neural Networks with Linear Teachers

[6:30] Continual Learning in the Teacher-Student Setup: Impact of Task Similarity

[6:35] A Functional Perspective on Learning Symmetric Functions with Neural Networks

[6:40] Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks

[6:45] On the Random Conjugate Kernel and Neural Tangent Kernel

Q&A s 6:50-6:55

[6:50] Q&A

(ends 7:00 AM)

Reinforcement Learning 1 [6:00-7:00]

Oral s 6:00-6:20

[6:00] Risk-Sensitive Reinforcement Learning with Function Approximation: A Debiasing Approach

Spotlight s 6:20-6:50

[6:20] Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity

[6:25] Neuro-algorithmic Policies Enable Fast Combinatorial Generalization

[6:30] PID Accelerated Value Iteration Algorithm

[6:35] Provably Efficient Learning of Transferable Rewards

[6:40] Reinforcement Learning for Cost-Aware Markov Decision Processes

[6:45] Value Alignment Verification

Q&A s 6:50-6:55

[6:50] Q&A

(ends 7:00 AM)

Optimization 1 [6:00-7:00]

Oral s 6:00-6:20

[6:00] PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization

Spotlight s 6:20-6:50

[6:20] Projection Robust Wasserstein Barycenters

[6:25] Efficient Message Passing for 0–1 ILPs with Binary Decision Diagrams

[6:30] Distributionally Robust Optimization with Markovian Data

[6:35] Acceleration via Fractal Learning Rate Schedules

[6:40] A Novel Sequential Coreset Method for Gradient Descent Algorithms

[6:45] Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More

Q&A s 6:50-6:55

[6:50] Q&A

(ends 7:00 AM)

Optimization (Convex) 1 [6:00-7:00]

Oral s 6:00-6:20

[6:00] Variance Reduction via Primal-Dual Accelerated Dual Averaging for Nonsmooth Convex Finite-Sums

Spotlight s 6:20-6:50

[6:20] Dueling Convex Optimization

[6:25] Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs

[6:30] Parameter-free Locally Accelerated Conditional Gradients

[6:35] Principal Component Hierarchy for Sparse Quadratic Programs

[6:40] One-sided Frank-Wolfe algorithms for saddle problems

[6:45] ConvexVST: A Convex Optimization Approach to Variance-stabilizing Transformation

Q&A s 6:50-6:55

[6:50] Q&A

(ends 7:00 AM)

Deep Generative Model 1 [6:00-7:00]

Oral s 6:00-6:20

[6:00] Oops I Took A Gradient: Scalable Sampling for Discrete Distributions

Spotlight s 6:20-6:50

[6:20] Multiscale Invertible Generative Networks for High-Dimensional Bayesian Inference

[6:25] GraphDF: A Discrete Flow Model for Molecular Graph Generation

[6:30] Hierarchical VAEs Know What They Don’t Know

[6:35] Order Matters: Probabilistic Modeling of Node Sequence for Graph Generation

[6:40] Generative Video Transformer: Can Objects be the Words?

[6:45] Poisson-Randomised DirBN: Large Mutation is Needed in Dirichlet Belief Networks

Q&A s 6:50-6:55

[6:50] Q&A

(ends 7:00 AM)

Deep Learning Algorithms 1 [6:00-7:00]

Oral s 6:00-6:20

[6:00] Leveraging Sparse Linear Layers for Debuggable Deep Networks

Spotlight s 6:20-6:50

[6:20] Voice2Series: Reprogramming Acoustic Models for Time Series Classification

[6:25] Self-Tuning for Data-Efficient Deep Learning

[6:30] How Framelets Enhance Graph Neural Networks

[6:35] Federated Continual Learning with Weighted Inter-client Transfer

[6:40] Self Normalizing Flows

[6:45] Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling

Q&A s 6:50-6:55

[6:50] Q&A

(ends 7:00 AM)

Deep Learning Algorithms 2 [6:00-7:00]

Oral s 6:00-6:20

[6:00] Principled Simplicial Neural Networks for Trajectory Prediction

Spotlight s 6:20-6:50

[6:20] Efficient Differentiable Simulation of Articulated Bodies

[6:25] On Monotonic Linear Interpolation of Neural Network Parameters

[6:30] Connecting Sphere Manifolds Hierarchically for Regularization

[6:35] Controlling Graph Dynamics with Reinforcement Learning and Graph Neural Networks

[6:40] Thinking Like Transformers

[6:45] Federated Learning of User Verification Models Without Sharing Embeddings

Q&A s 6:50-6:55

[6:50] Q&A

(ends 7:00 AM)

AutoML and Deep Architecture [6:00-7:00]

Oral s 6:00-6:20

[6:00] Neural Architecture Search without Training

Spotlight s 6:20-6:50

[6:20] Is Space-Time Attention All You Need for Video Understanding?

[6:25] A Probabilistic Approach to Neural Network Pruning

[6:30] KNAS: Green Neural Architecture Search

[6:35] Efficient Lottery Ticket Finding: Less Data is More

[6:40] ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases

[6:45] Provably Strict Generalisation Benefit for Equivariant Models

Q&A s 6:50-6:55

[6:50] Q&A

(ends 7:00 AM)

7 a.m.

Reinforcement Learning and Planning 1 [7:00-8:00]

Oral s 7:00-7:20

[7:00] World Model as a Graph: Learning Latent Landmarks for Planning

Spotlight s 7:20-7:45

[7:20] Revisiting Rainbow: Promoting more insightful and inclusive deep reinforcement learning research

[7:25] Deep Reinforcement Learning amidst Continual Structured Non-Stationarity

[7:30] Offline Reinforcement Learning with Pseudometric Learning

[7:35] EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL

[7:40] Decision-Making Under Selective Labels: Optimal Finite-Domain Policies and Beyond

Q&A s 7:45-7:50

[7:45] Q&A

(ends 8:00 AM)

Deep Learning Algorithms 4 [7:00-8:00]

Oral s 7:00-7:20

[7:00] Directional Graph Networks

Spotlight s 7:20-7:50

[7:20] Winograd Algorithm for AdderNet

[7:25] LieTransformer: Equivariant Self-Attention for Lie Groups

[7:30] "Hey, that's not an ODE": Faster ODE Adjoints via Seminorms

[7:35] Graph Mixture Density Networks

[7:40] Momentum Residual Neural Networks

[7:45] Better Training using Weight-Constrained Stochastic Dynamics

Q&A s 7:50-7:55

[7:50] Q&A

(ends 8:00 AM)

Deep Learning Algorithms 3 [7:00-8:00]

Oral s 7:00-7:20

[7:00] ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision

Spotlight s 7:20-7:50

[7:20] Learning Curves for Analysis of Deep Networks

[7:25] GLSearch: Maximum Common Subgraph Detection via Learning to Search

[7:30] Learning Intra-Batch Connections for Deep Metric Learning

[7:35] Simultaneous Similarity-based Self-Distillation for Deep Metric Learning

[7:40] Unifying Vision-and-Language Tasks via Text Generation

[7:45] DeepWalking Backwards: From Embeddings Back to Graphs

Q&A s 7:50-7:55

[7:50] Q&A

(ends 8:00 AM)

Reinforcement Learning and Planning 2 [7:00-8:00]

Oral s 7:00-7:20

[7:00] Skill Discovery for Exploration and Planning using Deep Skill Graphs

Spotlight s 7:20-7:50

[7:20] Learning Routines for Effective Off-Policy Reinforcement Learning

[7:25] PODS: Policy Optimization via Differentiable Simulation

[7:30] Learning and Planning in Complex Action Spaces

[7:35] Model-Based Reinforcement Learning via Latent-Space Collocation

[7:40] Vector Quantized Models for Planning

[7:45] LTL2Action: Generalizing LTL Instructions for Multi-Task RL

Q&A s 7:50-7:55

[7:50] Q&A

(ends 8:00 AM)

Deep Generative Model 2 [7:00-8:00]

Oral s 7:00-7:20

[7:00] Spectral Smoothing Unveils Phase Transitions in Hierarchical Variational Autoencoders

Spotlight s 7:20-7:50

[7:20] Riemannian Convex Potential Maps

[7:25] Autoencoding Under Normalization Constraints

[7:30] PixelTransformer: Sample Conditioned Signal Generation

[7:35] Generative Adversarial Networks for Markovian Temporal Dynamics: Stochastic Continuous Data Generation

[7:40] Autoencoder Image Interpolation by Shaping the Latent Space

[7:45] Improved Denoising Diffusion Probabilistic Models

Q&A s 7:50-7:55

[7:50] Q&A

(ends 8:00 AM)

AutoML and Neural Network Architectures 1 [7:00-8:00]

Oral s 7:00-7:20

[7:00] OmniNet: Omnidirectional Representations from Transformers

Spotlight s 7:20-7:45

[7:20] Boosting the Throughput and Accelerator Utilization of Specialized CNN Inference Beyond Increasing Batch Size

[7:25] E(n) Equivariant Graph Neural Networks

[7:30] Grid-Functioned Neural Networks

[7:35] MSA Transformer

[7:40] Parallelizing Legendre Memory Unit Training

Q&A s 7:45-7:50

[7:45] Q&A

(ends 8:00 AM)

Deep Learning 1 [7:00-8:00]

Oral s 7:00-7:20

[7:00] Not All Memories are Created Equal: Learning to Forget by Expiring

Spotlight s 7:20-7:50

[7:20] Learning Bounds for Open-Set Learning

[7:25] Perceiver: General Perception with Iterative Attention

[7:30] Synthesizer: Rethinking Self-Attention for Transformer Models

[7:35] Slot Machines: Discovering Winning Combinations of Random Weights in Neural Networks

[7:40] What's in the Box? Exploring the Inner Life of Neural Networks with Robust Rules

[7:45] Neural-Pull: Learning Signed Distance Function from Point clouds by Learning to Pull Space onto Surface

Q&A s 7:50-7:55

[7:50] Q&A

(ends 8:00 AM)

Optimization 2 [7:00-8:00]

Oral s 7:00-7:20

[7:00] Stability and Convergence of Stochastic Gradient Clipping: Beyond Lipschitz Continuity and Smoothness

Spotlight s 7:20-7:50

[7:20] Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization

[7:25] Variational Data Assimilation with a Learned Inverse Observation Operator

[7:30] Fast Projection Onto Convex Smooth Constraints

[7:35] Decomposable Submodular Function Minimization via Maximum Flow

[7:40] Multiplicative Noise and Heavy Tails in Stochastic Optimization

[7:45] Distributed Second Order Methods with Fast Rates and Compressed Communication

Q&A s 7:50-7:55

[7:50] Q&A

(ends 8:00 AM)

Reinforcement Learning 2 [7:00-8:00]

Oral s 7:00-7:20

[7:00] Coach-Player Multi-agent Reinforcement Learning for Dynamic Team Composition

Spotlight s 7:20-7:50

[7:20] Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning

[7:25] A New Formalism, Method and Open Issues for Zero-Shot Coordination

[7:30] Targeted Data Acquisition for Evolving Negotiation Agents

[7:35] Inverse Constrained Reinforcement Learning

[7:40] Counterfactual Credit Assignment in Model-Free Reinforcement Learning

[7:45] Interactive Learning from Activity Description

Q&A s 7:50-7:55

[7:50] Q&A

(ends 8:00 AM)

8 a.m.

Invited Talk:

Rethinking Drug Discovery in the Era of Digital Biology

Daphne Koller

(ends 9:00 AM)

Affinity Workshop:

Queer in AI Workshop

(ends 5:00 PM)

9 a.m.

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

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

Winograd Algorithm for AdderNet

Fast Projection Onto Convex Smooth Constraints

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

Zeroth-Order Non-Convex Learning via Hierarchical Dual Averaging

LTL2Action: Generalizing LTL Instructions for Multi-Task RL

Directional Graph Networks

Learning Bounds for Open-Set Learning

Voice2Series: Reprogramming Acoustic Models for Time Series Classification

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

Learning Intra-Batch Connections for Deep Metric Learning

Oops I Took A Gradient: Scalable Sampling for Discrete Distributions

Interpretable Stability Bounds for Spectral Graph Filters

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

Consistent Nonparametric Methods for Network Assisted Covariate Estimation

Asynchronous Decentralized Optimization With Implicit Stochastic Variance Reduction

Targeted Data Acquisition for Evolving Negotiation Agents

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

Momentum Residual Neural Networks

Learning Task Informed Abstractions

A Functional Perspective on Learning Symmetric Functions with Neural Networks

Generative Adversarial Transformers

Bayesian Deep Learning via Subnetwork Inference

Thinking Like Transformers

Efficient Differentiable Simulation of Articulated Bodies

UnICORNN: A recurrent model for learning very long time dependencies

Self-Tuning for Data-Efficient Deep Learning

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

Interactive Learning from Activity Description

Decoupling Value and Policy for Generalization in Reinforcement Learning

Decentralized Riemannian Gradient Descent on the Stiefel Manifold

On the Random Conjugate Kernel and Neural Tangent Kernel

PID Accelerated Value Iteration Algorithm

Grid-Functioned Neural Networks

Dueling Convex Optimization

Multiplicative Noise and Heavy Tails in Stochastic Optimization

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

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

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

Inverse Constrained Reinforcement Learning

Order Matters: Probabilistic Modeling of Node Sequence for Graph Generation

Hierarchical VAEs Know What They Don’t Know

Graph Mixture Density Networks

Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning

GLSearch: Maximum Common Subgraph Detection via Learning to Search

Unsupervised Learning of Visual 3D Keypoints for Control

Demonstration-Conditioned Reinforcement Learning for Few-Shot Imitation

Reinforcement Learning with Prototypical Representations

Zoo-Tuning: Adaptive Transfer from A Zoo of Models

Breaking the Limits of Message Passing Graph Neural Networks

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

PixelTransformer: Sample Conditioned Signal Generation

Muesli: Combining Improvements in Policy Optimization

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

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

Provably Strict Generalisation Benefit for Equivariant Models

Unbalanced minibatch Optimal Transport; applications to Domain Adaptation

Size-Invariant Graph Representations for Graph Classification Extrapolations

State Entropy Maximization with Random Encoders for Efficient Exploration

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

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

Sparsifying Networks via Subdifferential Inclusion

Provably Efficient Learning of Transferable Rewards

Connecting Sphere Manifolds Hierarchically for Regularization

Skill Discovery for Exploration and Planning using Deep Skill Graphs

What Are Bayesian Neural Network Posteriors Really Like?

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

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

Unifying Vision-and-Language Tasks via Text Generation

Generative Video Transformer: Can Objects be the Words?

World Model as a Graph: Learning Latent Landmarks for Planning

Generative Particle Variational Inference via Estimation of Functional Gradients

Learning Curves for Analysis of Deep Networks

Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning

Fundamental Tradeoffs in Distributionally Adversarial Training

Scalable Computations of Wasserstein Barycenter via Input Convex Neural Networks

Self Normalizing Flows

Parameter-free Locally Accelerated Conditional Gradients

Projection Robust Wasserstein Barycenters

Outlier-Robust Optimal Transport

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

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

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

Vector Quantized Models for Planning

Principled Simplicial Neural Networks for Trajectory Prediction

Optimal Complexity in Decentralized Training

OmniNet: Omnidirectional Representations from Transformers

Better Training using Weight-Constrained Stochastic Dynamics

HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search

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

Deeply-Debiased Off-Policy Interval Estimation

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

Preferential Temporal Difference Learning

Model-Based Reinforcement Learning via Latent-Space Collocation

Explainable Automated Graph Representation Learning with Hyperparameter Importance

Evolving Attention with Residual Convolutions

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

Riemannian Convex Potential Maps

Acceleration via Fractal Learning Rate Schedules

Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot

Offline Contextual Bandits with Overparameterized Models

Decomposable Submodular Function Minimization via Maximum Flow

Efficient Lottery Ticket Finding: Less Data is More

A Unified Lottery Ticket Hypothesis for Graph Neural Networks

MC-LSTM: Mass-Conserving LSTM

Improved Denoising Diffusion Probabilistic Models

On the Optimality of Batch Policy Optimization Algorithms

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

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

Newton Method over Networks is Fast up to the Statistical Precision

From Local Structures to Size Generalization in Graph Neural Networks

Low-Rank Sinkhorn Factorization

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

MSA Transformer

Federated Continual Learning with Weighted Inter-client Transfer

ConvexVST: A Convex Optimization Approach to Variance-stabilizing Transformation

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

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

How Framelets Enhance Graph Neural Networks

Distributed Second Order Methods with Fast Rates and Compressed Communication

BORE: Bayesian Optimization by Density-Ratio Estimation

Reinforcement Learning for Cost-Aware Markov Decision Processes

LieTransformer: Equivariant Self-Attention for Lie Groups

Bias-Robust Bayesian Optimization via Dueling Bandits

Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks

Deep Reinforcement Learning amidst Continual Structured Non-Stationarity

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

Variational Data Assimilation with a Learned Inverse Observation Operator

A Novel Sequential Coreset Method for Gradient Descent Algorithms

Dataset Dynamics via Gradient Flows in Probability Space

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

PODS: Policy Optimization via Differentiable Simulation

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

Neural Symbolic Regression that scales

Spectral Smoothing Unveils Phase Transitions in Hierarchical Variational Autoencoders

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

Autoencoder Image Interpolation by Shaping the Latent Space

Strategic Classification Made Practical

A Probabilistic Approach to Neural Network Pruning

On Monotonic Linear Interpolation of Neural Network Parameters

Controlling Graph Dynamics with Reinforcement Learning and Graph Neural Networks

Distributionally Robust Optimization with Markovian Data

Sliced Iterative Normalizing Flows

Federated Learning of User Verification Models Without Sharing Embeddings

Large-Margin Contrastive Learning with Distance Polarization Regularizer

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

AutoSampling: Search for Effective Data Sampling Schedules

Counterfactual Credit Assignment in Model-Free Reinforcement Learning

Parallelizing Legendre Memory Unit Training

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

Value Alignment Verification

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

Federated Learning under Arbitrary Communication Patterns

E(n) Equivariant Graph Neural Networks

Multiscale Invertible Generative Networks for High-Dimensional Bayesian Inference

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

KNAS: Green Neural Architecture Search

Neuro-algorithmic Policies Enable Fast Combinatorial Generalization

Deep kernel processes

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

Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling

Neural Architecture Search without Training

ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases

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

Simultaneous Similarity-based Self-Distillation for Deep Metric Learning

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

Perceiver: General Perception with Iterative Attention

Principal Component Hierarchy for Sparse Quadratic Programs

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

Towards Understanding Learning in Neural Networks with Linear Teachers

Exploiting structured data for learning contagious diseases under incomplete testing

Learning and Planning in Complex Action Spaces

Stochastic Sign Descent Methods: New Algorithms and Better Theory

Imitation by Predicting Observations

GraphDF: A Discrete Flow Model for Molecular Graph Generation

Offline Reinforcement Learning with Pseudometric Learning

Relative Positional Encoding for Transformers with Linear Complexity

Autoencoding Under Normalization Constraints

DeepWalking Backwards: From Embeddings Back to Graphs

Learning Routines for Effective Off-Policy Reinforcement Learning

Leveraging Sparse Linear Layers for Debuggable Deep Networks

A New Representation of Successor Features for Transfer across Dissimilar Environments

Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning

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

One-sided Frank-Wolfe algorithms for saddle problems

Synthesizer: Rethinking Self-Attention for Transformer Models

UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning

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

Phasic Policy Gradient

(ends 11:00 AM)

11 a.m.

Town Hall:

Town Hall

(ends 12:00 PM)

5 p.m.

Optimization and Algorithms 1 [5:00-6:00]

Oral s 5:00-5:20

[5:00] A Tale of Two Efficient and Informative Negative Sampling Distributions

Spotlight s 5:20-5:50

[5:20] TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models

[5:25] Quantization Algorithms for Random Fourier Features

[5:30] Rethinking Neural vs. Matrix-Factorization Collaborative Filtering: the Theoretical Perspectives

[5:35] Concentric mixtures of Mallows models for top-$k$ rankings: sampling and identifiability

[5:40] Heterogeneity for the Win: One-Shot Federated Clustering

[5:45] Cross-Gradient Aggregation for Decentralized Learning from Non-IID Data

Q&A s 5:50-5:55

[5:50] Q&A

(ends 6:00 PM)

Deep Learning Algorithms 5 [5:00-6:00]

Oral s 5:00-5:20

[5:00] A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups

Spotlight s 5:20-5:50

[5:20] Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework

[5:25] The Earth Mover's Pinball Loss: Quantiles for Histogram-Valued Regression

[5:30] Signatured Deep Fictitious Play for Mean Field Games with Common Noise

[5:35] Equivariant message passing for the prediction of tensorial properties and molecular spectra

[5:40] Improving Breadth-Wise Backpropagation in Graph Neural Networks Helps Learning Long-Range Dependencies.

[5:45] LARNet: Lie Algebra Residual Network for Face Recognition

Q&A s 5:50-5:55

[5:50] Q&A

(ends 6:00 PM)

Reinforcement Learning and Planning 3 [5:00-6:00]

Oral s 5:00-5:20

[5:00] PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning

Spotlight s 5:20-5:50

[5:20] Safe Reinforcement Learning with Linear Function Approximation

[5:25] Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks

[5:30] Offline Reinforcement Learning with Fisher Divergence Critic Regularization

[5:35] Recomposing the Reinforcement Learning Building Blocks with Hypernetworks

[5:40] OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation

[5:45] Discovering symbolic policies with deep reinforcement learning

Q&A s 5:50-5:55

[5:50] Q&A

(ends 6:00 PM)

Deep Learning 2 [5:00-6:00]

Oral s 5:00-5:20

[5:00] Characterizing Structural Regularities of Labeled Data in Overparameterized Models

Spotlight s 5:20-5:50

[5:20] Stabilizing Equilibrium Models by Jacobian Regularization

[5:25] On the Predictability of Pruning Across Scales

[5:30] Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?

[5:35] LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning

[5:40] Dense for the Price of Sparse: Improved Performance of Sparsely Initialized Networks via a Subspace Offset

[5:45] Learning Neural Network Subspaces

Q&A s 5:50-5:55

[5:50] Q&A

(ends 6:00 PM)

Optimization 3 [5:00-6:00]

Oral s 5:00-5:20

[5:00] On the price of explainability for some clustering problems

Spotlight s 5:20-5:50

[5:20] Instance Specific Approximations for Submodular Maximization

[5:25] Adapting to Delays and Data in Adversarial Multi-Armed Bandits

[5:30] Structured Convolutional Kernel Networks for Airline Crew Scheduling

[5:35] Online Graph Dictionary Learning

[5:40] Stochastic Iterative Graph Matching

[5:45] Training Quantized Neural Networks to Global Optimality via Semidefinite Programming

Q&A s 5:50-5:55

[5:50] Q&A

(ends 6:00 PM)

Reinforcement Learning 4 [5:00-6:00]

Oral s 5:00-5:20

[5:00] Robust Asymmetric Learning in POMDPs

Spotlight s 5:20-5:50

[5:20] Differentiable Spatial Planning using Transformers

[5:25] Convex Regularization in Monte-Carlo Tree Search

[5:30] On-Policy Deep Reinforcement Learning for the Average-Reward Criterion

[5:35] Multi-Task Reinforcement Learning with Context-based Representations

[5:40] High Confidence Generalization for Reinforcement Learning

[5:45] Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards

Q&A s 5:50-5:55

[5:50] Q&A

(ends 6:00 PM)

Reinforcement Learning 3 [5:00-6:00]

Oral s 5:00-5:20

[5:00] Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning

Spotlight s 5:20-5:50

[5:20] Re-understanding Finite-State Representations of Recurrent Policy Networks

[5:25] Emergent Social Learning via Multi-agent Reinforcement Learning

[5:30] From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization

[5:35] Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills

[5:40] Trajectory Diversity for Zero-Shot Coordination

[5:45] FOP: Factorizing Optimal Joint Policy of Maximum-Entropy Multi-Agent Reinforcement Learning

Q&A s 5:50-5:55

[5:50] Q&A

(ends 6:00 PM)

Deep Generative Model 3 [5:00-6:00]

Oral s 5:00-5:20

[5:00] NeRF-VAE: A Geometry Aware 3D Scene Generative Model

Spotlight s 5:20-5:50

[5:20] Quantitative Understanding of VAE as a Non-linearly Scaled Isometric Embedding

[5:25] Soft then Hard: Rethinking the Quantization in Neural Image Compression

[5:30] Improved Contrastive Divergence Training of Energy-Based Models

[5:35] Deep Generative Learning via Schrödinger Bridge

[5:40] Partially Observed Exchangeable Modeling

[5:45] Understanding Failures in Out-of-Distribution Detection with Deep Generative Models

Q&A s 5:50-5:55

[5:50] Q&A

(ends 6:00 PM)

Deep Learning Algorithms 6 [5:00-6:00]

Oral s 5:00-5:20

[5:00] CATE: Computation-aware Neural Architecture Encoding with Transformers

Spotlight s 5:20-5:50

[5:20] What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?

[5:25] Towards Domain-Agnostic Contrastive Learning

[5:30] Joining datasets via data augmentation in the label space for neural networks

[5:35] Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision

[5:40] Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation

[5:45] Poolingformer: Long Document Modeling with Pooling Attention

Q&A s 5:50-5:55

[5:50] Q&A

(ends 6:00 PM)

6 p.m.

Optimization and Algorithms 2 [6:00-7:00]

Oral s 6:00-6:20

[6:00] Network Inference and Influence Maximization from Samples

Spotlight s 6:20-6:50

[6:20] Regularized Submodular Maximization at Scale

[6:25] Marginal Contribution Feature Importance - an Axiomatic Approach for Explaining Data

[6:30] Connecting Interpretability and Robustness in Decision Trees through Separation

[6:35] Light RUMs

[6:40] Submodular Maximization subject to a Knapsack Constraint: Combinatorial Algorithms with Near-optimal Adaptive Complexity

[6:45] CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints

Q&A s 6:50-6:55

[6:50] Q&A

(ends 7:00 PM)

Algorithms 1 [6:00-7:00]

Oral s 6:00-6:20

[6:00] A Wasserstein Minimax Framework for Mixed Linear Regression

Spotlight s 6:20-6:50

[6:20] Weight-covariance alignment for adversarially robust neural networks

[6:25] Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss

[6:30] Communication-Efficient Distributed SVD via Local Power Iterations

[6:35] A Riemannian Block Coordinate Descent Method for Computing the Projection Robust Wasserstein Distance

[6:40] Probabilistic Sequential Shrinking: A Best Arm Identification Algorithm for Stochastic Bandits with Corruptions

[6:45] Leveraging Language to Learn Program Abstractions and Search Heuristics

Q&A s 6:50-6:55

[6:50] Q&A

(ends 7:00 PM)

Reinforcement Learning 6 [6:00-7:00]

Oral s 6:00-6:20

[6:00] Decoupling Value and Policy for Generalization in Reinforcement Learning

Spotlight s 6:20-6:50

[6:20] Prioritized Level Replay

[6:25] SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies

[6:30] GMAC: A Distributional Perspective on Actor-Critic Framework

[6:35] Goal-Conditioned Reinforcement Learning with Imagined Subgoals

[6:40] Policy Gradient Bayesian Robust Optimization for Imitation Learning

[6:45] Reinforcement Learning of Implicit and Explicit Control Flow Instructions

Q&A s 6:50-6:55

[6:50] Q&A

(ends 7:00 PM)

Deep Learning Algorithms and Applications [6:00-7:00]

Oral s 6:00-6:20

[6:00] Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies

Spotlight s 6:20-6:45

[6:20] EfficientNetV2: Smaller Models and Faster Training

[6:25] Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning

[6:30] LAMDA: Label Matching Deep Domain Adaptation

[6:35] Temporally Correlated Task Scheduling for Sequence Learning

[6:40] Information Obfuscation of Graph Neural Networks

Q&A s 6:45-6:50

[6:45] Q&A

(ends 7:00 PM)

AutoML [6:00-7:00]

Spotlight s 6:00-6:15

[6:00] iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients

[6:05] Accurate Post Training Quantization With Small Calibration Sets

[6:10] Optimal Transport Kernels for Sequential and Parallel Neural Architecture Search

Oral s 6:15-6:35

[6:15] Few-Shot Neural Architecture Search

Spotlight s 6:35-6:50

[6:35] AutoAttend: Automated Attention Representation Search

[6:40] Think Global and Act Local: Bayesian Optimisation over High-Dimensional Categorical and Mixed Search Spaces

[6:45] Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators

Q&A s 6:50-6:55

[6:50] Q&A

(ends 7:00 PM)

Reinforcement Learning 5 [6:00-7:00]

Oral s 6:00-6:20

[6:00] The Emergence of Individuality

Spotlight s 6:20-6:45

[6:20] DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning

[6:25] From Local to Global Norm Emergence: Dissolving Self-reinforcing Substructures with Incremental Social Instruments

[6:30] Learning While Playing in Mean-Field Games: Convergence and Optimality

[6:35] Learning Fair Policies in Decentralized Cooperative Multi-Agent Reinforcement Learning

[6:40] Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment

Q&A s 6:45-6:50

[6:45] Q&A

(ends 7:00 PM)

Reinforcement Learning 7 [6:00-7:00]

Oral s 6:00-6:20

[6:00] PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training

Spotlight s 6:20-6:50

[6:20] Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning

[6:25] Keyframe-Focused Visual Imitation Learning

[6:30] Learning and Planning in Average-Reward Markov Decision Processes

[6:35] Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing

[6:40] Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision

[6:45] Emphatic Algorithms for Deep Reinforcement Learning

Q&A s 6:50-6:55

[6:50] Q&A

(ends 7:00 PM)

Optimization (Stochastic) [6:00-7:00]

Oral s 6:00-6:20

[6:00] The Power of Adaptivity for Stochastic Submodular Cover

Spotlight s 6:20-6:50

[6:20] The Heavy-Tail Phenomenon in SGD

[6:25] Federated Composite Optimization

[6:30] On Estimation in Latent Variable Models

[6:35] Asynchronous Distributed Learning : Adapting to Gradient Delays without Prior Knowledge

[6:40] Randomized Algorithms for Submodular Function Maximization with a $k$-System Constraint

[6:45] BASGD: Buffered Asynchronous SGD for Byzantine Learning

Q&A s 6:50-6:55

[6:50] Q&A

(ends 7:00 PM)

Deep Generative Model 4 [6:00-7:00]

Oral s 6:00-6:20

[6:00] Generating images with sparse representations

Spotlight s 6:20-6:50

[6:20] An Identifiable Double VAE For Disentangled Representations

[6:25] A Unified Generative Adversarial Network Training via Self-Labeling and Self-Attention

[6:30] On Characterizing GAN Convergence Through Proximal Duality Gap

[6:35] Scalable Normalizing Flows for Permutation Invariant Densities

[6:40] Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics

[6:45] Zero-Shot Text-to-Image Generation

Q&A s 6:50-6:55

[6:50] Q&A

(ends 7:00 PM)

7 p.m.

Deep Reinforcement Learning 3 [7:00-8:00]

Oral s 7:00-7:20

[7:00] Cooperative Exploration for Multi-Agent Deep Reinforcement Learning

Spotlight s 7:20-7:50

[7:20] A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation

[7:25] Learning to Weight Imperfect Demonstrations

[7:30] DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning

[7:35] MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning

[7:40] RRL: Resnet as representation for Reinforcement Learning

[7:45] SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II

Q&A s 7:50-7:55

[7:50] Q&A

(ends 8:00 PM)

AutoML and Neural Network Architectures 2 [7:00-8:00]

Oral s 7:00-7:20

[7:00] AlphaNet: Improved Training of Supernets with Alpha-Divergence

Spotlight s 7:20-7:50

[7:20] Catformer: Designing Stable Transformers via Sensitivity Analysis

[7:25] A Receptor Skeleton for Capsule Neural Networks

[7:30] Explore Visual Concept Formation for Image Classification

[7:35] K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernets

[7:40] High-Performance Large-Scale Image Recognition Without Normalization

[7:45] Lipschitz normalization for self-attention layers with application to graph neural networks

Q&A s 7:50-7:55

[7:50] Q&A

(ends 8:00 PM)

Optimization (Convex) 2 [7:00-8:00]

Oral s 7:00-7:20

[7:00] Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with O(1/k^2) Rate on Squared Gradient Norm

Spotlight s 7:20-7:50

[7:20] Communication-Efficient Distributed Optimization with Quantized Preconditioners

[7:25] Optimal regret algorithm for Pseudo-1d Bandit Convex Optimization

[7:30] Fast Stochastic Bregman Gradient Methods: Sharp Analysis and Variance Reduction

[7:35] Moreau-Yosida $f$-divergences

[7:40] Affine Invariant Analysis of Frank-Wolfe on Strongly Convex Sets

[7:45] On a Combination of Alternating Minimization and Nesterov's Momentum

Q&A s 7:50-7:55

[7:50] Q&A

(ends 8:00 PM)

Reinforcement Learning 8 [7:00-8:00]

Oral s 7:00-7:20

[7:00] Inverse Decision Modeling: Learning Interpretable Representations of Behavior

Spotlight s 7:20-7:50

[7:20] On Proximal Policy Optimization's Heavy-tailed Gradients

[7:25] Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning

[7:30] Variational Empowerment as Representation Learning for Goal-Conditioned Reinforcement Learning

[7:35] Is Pessimism Provably Efficient for Offline RL?

[7:40] Beyond Variance Reduction: Understanding the True Impact of Baselines on Policy Optimization

[7:45] Density Constrained Reinforcement Learning

Q&A s 7:50-7:55

[7:50] Q&A

(ends 8:00 PM)

Optimization 4 [7:00-8:00]

Oral s 7:00-7:20

[7:00] Sequential Domain Adaptation by Synthesizing Distributionally Robust Experts

Spotlight s 7:20-7:50

[7:20] Oblivious Sketching-based Central Path Method for Linear Programming

[7:25] Bayesian Optimization over Hybrid Spaces

[7:30] Variational (Gradient) Estimate of the Score Function in Energy-based Latent Variable Models

[7:35] Compositional Video Synthesis with Action Graphs

[7:40] Neural Pharmacodynamic State Space Modeling

[7:45] Three Operator Splitting with a Nonconvex Loss Function

Q&A s 7:50-7:55

[7:50] Q&A

(ends 8:00 PM)

Large Scale Optimization [7:00-8:00]

Oral s 7:00-7:20

[7:00] ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training

Spotlight s 7:20-7:50

[7:20] Householder Sketch for Accurate and Accelerated Least-Mean-Squares Solvers

[7:25] Accumulated Decoupled Learning with Gradient Staleness Mitigation for Convolutional Neural Networks

[7:30] Training Graph Neural Networks with 1000 Layers

[7:35] 1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed

[7:40] Federated Deep AUC Maximization for Hetergeneous Data with a Constant Communication Complexity

[7:45] Ditto: Fair and Robust Federated Learning Through Personalization

Q&A s 7:50-7:55

[7:50] Q&A

(ends 8:00 PM)

Deep Learning Algorithms 7 [7:00-8:00]

Oral s 7:00-7:20

[7:00] Out-of-Distribution Generalization via Risk Extrapolation (REx)

Spotlight s 7:20-7:50

[7:20] What Makes for End-to-End Object Detection?

[7:25] On Explainability of Graph Neural Networks via Subgraph Explorations

[7:30] Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks

[7:35] Data Augmentation for Meta-Learning

[7:40] Understanding Invariance via Feedforward Inversion of Discriminatively Trained Classifiers

[7:45] Neural Symbolic Regression that scales

Q&A s 7:50-7:55

[7:50] Q&A

(ends 8:00 PM)

Reinforcement Learning 9 [7:00-8:00]

Oral s 7:00-7:20

[7:00] Hyperparameter Selection for Imitation Learning

Spotlight s 7:20-7:50

[7:20] Revisiting Peng's Q($\lambda$) for Modern Reinforcement Learning

[7:25] Monotonic Robust Policy Optimization with Model Discrepancy

[7:30] Taylor Expansion of Discount Factors

[7:35] Generalizable Episodic Memory for Deep Reinforcement Learning

[7:40] Representation Matters: Offline Pretraining for Sequential Decision Making

[7:45] Reinforcement Learning Under Moral Uncertainty

Q&A s 7:50-7:55

[7:50] Q&A

(ends 8:00 PM)

Deep Learning Algorithms 8 [7:00-8:00]

Oral s 7:00-7:20

[7:00] Just Train Twice: Improving Group Robustness without Training Group Information

Spotlight s 7:20-7:50

[7:20] Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth

[7:25] GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training

[7:30] A Bit More Bayesian: Domain-Invariant Learning with Uncertainty

[7:35] Neural Rough Differential Equations for Long Time Series

[7:40] Whitening and Second Order Optimization Both Make Information in the Dataset Unusable During Training, and Can Reduce or Prevent Generalization

[7:45] Data augmentation for deep learning based accelerated MRI reconstruction with limited data

Q&A s 7:50-7:55

[7:50] Q&A

(ends 8:00 PM)

8 p.m.

Invited Talk:

Cryospheric Science and Emergence of Machine Learning

Xiao Cunde · Qin Dahe

(ends 9:00 PM)

9 p.m.

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

Training Quantized Neural Networks to Global Optimality via Semidefinite Programming

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

Variational Empowerment as Representation Learning for Goal-Conditioned Reinforcement Learning

AlphaNet: Improved Training of Supernets with Alpha-Divergence

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

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

CATE: Computation-aware Neural Architecture Encoding with Transformers

Taylor Expansion of Discount Factors

On the price of explainability for some clustering problems

Soft then Hard: Rethinking the Quantization in Neural Image Compression

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

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

BASGD: Buffered Asynchronous SGD for Byzantine Learning

Sequential Domain Adaptation by Synthesizing Distributionally Robust Experts

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

Federated Composite Optimization

LARNet: Lie Algebra Residual Network for Face Recognition

Representation Matters: Offline Pretraining for Sequential Decision Making

Partially Observed Exchangeable Modeling

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

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

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

Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies

On Characterizing GAN Convergence Through Proximal Duality Gap

GMAC: A Distributional Perspective on Actor-Critic Framework

Characterizing Structural Regularities of Labeled Data in Overparameterized Models

GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training

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

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

Safe Reinforcement Learning with Linear Function Approximation

Is Pessimism Provably Efficient for Offline RL?

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

OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation

Generalizable Episodic Memory for Deep Reinforcement Learning

Re-understanding Finite-State Representations of Recurrent Policy Networks

A Wasserstein Minimax Framework for Mixed Linear Regression

Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks

Cooperative Exploration for Multi-Agent Deep Reinforcement Learning

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

Towards Domain-Agnostic Contrastive Learning

Moreau-Yosida $f$-divergences

Training Graph Neural Networks with 1000 Layers

Generating images with sparse representations

Optimal regret algorithm for Pseudo-1d Bandit Convex Optimization

Fast Stochastic Bregman Gradient Methods: Sharp Analysis and Variance Reduction

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

Learning Fair Policies in Decentralized Cooperative Multi-Agent Reinforcement Learning

Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills

Structured Convolutional Kernel Networks for Airline Crew Scheduling

Recomposing the Reinforcement Learning Building Blocks with Hypernetworks

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

Data Augmentation for Meta-Learning

DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning

Just Train Twice: Improving Group Robustness without Training Group Information

Learning and Planning in Average-Reward Markov Decision Processes

Instance Specific Approximations for Submodular Maximization

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

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

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

Differentiable Spatial Planning using Transformers

Reinforcement Learning Under Moral Uncertainty

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

Poolingformer: Long Document Modeling with Pooling Attention

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

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

Regularized Submodular Maximization at Scale

Prioritized Level Replay

Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision

On a Combination of Alternating Minimization and Nesterov's Momentum

Ditto: Fair and Robust Federated Learning Through Personalization

Leveraging Language to Learn Program Abstractions and Search Heuristics

Three Operator Splitting with a Nonconvex Loss Function

Hyperparameter Selection for Imitation Learning

Temporally Correlated Task Scheduling for Sequence Learning

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

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

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

A Tale of Two Efficient and Informative Negative Sampling Distributions

AutoAttend: Automated Attention Representation Search

Affine Invariant Analysis of Frank-Wolfe on Strongly Convex Sets

On the Predictability of Pruning Across Scales

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

On Estimation in Latent Variable Models

Multi-Task Reinforcement Learning with Context-based Representations

LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning

What Makes for End-to-End Object Detection?

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

Accumulated Decoupled Learning with Gradient Staleness Mitigation for Convolutional Neural Networks

Asynchronous Distributed Learning : Adapting to Gradient Delays without Prior Knowledge

Deep Generative Learning via Schrödinger Bridge

Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards

iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients

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

On Proximal Policy Optimization's Heavy-tailed Gradients

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

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

Accurate Post Training Quantization With Small Calibration Sets

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

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

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

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

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

Emphatic Algorithms for Deep Reinforcement Learning

Connecting Interpretability and Robustness in Decision Trees through Separation

Stabilizing Equilibrium Models by Jacobian Regularization

Network Inference and Influence Maximization from Samples

Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework

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

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

Goal-Conditioned Reinforcement Learning with Imagined Subgoals

Discovering symbolic policies with deep reinforcement learning

Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing

Few-Shot Neural Architecture Search

High Confidence Generalization for Reinforcement Learning

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

Signatured Deep Fictitious Play for Mean Field Games with Common Noise

Scalable Normalizing Flows for Permutation Invariant Densities

Zero-Shot Text-to-Image Generation

Explore Visual Concept Formation for Image Classification

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

Marginal Contribution Feature Importance - an Axiomatic Approach for Explaining Data

Trajectory Diversity for Zero-Shot Coordination

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

Bayesian Optimization over Hybrid Spaces

Quantization Algorithms for Random Fourier Features

The Emergence of Individuality

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

Light RUMs

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

Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning

Improved Contrastive Divergence Training of Energy-Based Models

Keyframe-Focused Visual Imitation Learning

Reinforcement Learning of Implicit and Explicit Control Flow Instructions

High-Performance Large-Scale Image Recognition Without Normalization

Learning to Weight Imperfect Demonstrations

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

Monotonic Robust Policy Optimization with Model Discrepancy

Convex Regularization in Monte-Carlo Tree Search

Inverse Decision Modeling: Learning Interpretable Representations of Behavior

Stochastic Iterative Graph Matching

Weight-covariance alignment for adversarially robust neural networks

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

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

Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics

Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss

Online Graph Dictionary Learning

On Explainability of Graph Neural Networks via Subgraph Explorations

An Identifiable Double VAE For Disentangled Representations

Emergent Social Learning via Multi-agent Reinforcement Learning

Information Obfuscation of Graph Neural Networks

The Heavy-Tail Phenomenon in SGD

Policy Gradient Bayesian Robust Optimization for Imitation Learning

LAMDA: Label Matching Deep Domain Adaptation

Compositional Video Synthesis with Action Graphs

The Power of Adaptivity for Stochastic Submodular Cover

Robust Asymmetric Learning in POMDPs

Density Constrained Reinforcement Learning

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

A Receptor Skeleton for Capsule Neural Networks

A Bit More Bayesian: Domain-Invariant Learning with Uncertainty

Offline Reinforcement Learning with Fisher Divergence Critic Regularization

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

Communication-Efficient Distributed SVD via Local Power Iterations

Catformer: Designing Stable Transformers via Sensitivity Analysis

Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning

Communication-Efficient Distributed Optimization with Quantized Preconditioners

Heterogeneity for the Win: One-Shot Federated Clustering

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

RRL: Resnet as representation for Reinforcement Learning

Optimal Transport Kernels for Sequential and Parallel Neural Architecture Search

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

Learning Neural Network Subspaces

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

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

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

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

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

EfficientNetV2: Smaller Models and Faster Training

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

Oblivious Sketching-based Central Path Method for Linear Programming

Neural Rough Differential Equations for Long Time Series

(ends 11:00 PM)

WED 21 JUL

5 a.m.

Reinforcement Learning 10 [5:00-6:00]

Oral s 5:00-5:20

[5:00] Cross-domain Imitation from Observations

Spotlight s 5:20-5:50

[5:20] SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning

[5:25] Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices

[5:30] Active Feature Acquisition with Generative Surrogate Models

[5:35] Characterizing the Gap Between Actor-Critic and Policy Gradient

[5:40] Spectral Normalisation for Deep Reinforcement Learning: An Optimisation Perspective

[5:45] Accelerating Safe Reinforcement Learning with Constraint-mismatched Baseline Policies

Q&A s 5:50-5:55

[5:50] Q&A

(ends 6:00 AM)

Learning Theory 1 [5:00-6:00]

Oral s 5:00-5:20

[5:00] Near Optimal Reward-Free Reinforcement Learning

Spotlight s 5:20-5:50

[5:20] Batch Value-function Approximation with Only Realizability

[5:25] Adversarial Combinatorial Bandits with General Non-linear Reward Functions

[5:30] Model-Free and Model-Based Policy Evaluation when Causality is Uncertain

[5:35] Bootstrapping Fitted Q-Evaluation for Off-Policy Inference

[5:40] On Learnability via Gradient Method for Two-Layer ReLU Neural Networks in Teacher-Student Setting

[5:45] Spectral vertex sparsifiers and pair-wise spanners over distributed graphs

Q&A s 5:50-5:55

[5:50] Q&A

(ends 6:00 AM)

Deep Learning Theory 2 [5:00-6:00]

Oral s 5:00-5:20

[5:00] On Energy-Based Models with Overparametrized Shallow Neural Networks

Spotlight s 5:20-5:50

[5:20] Uncertainty Principles of Encoding GANs

[5:25] On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths

[5:30] Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks

[5:35] Functional Space Analysis of Local GAN Convergence

[5:40] Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models

[5:45] Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise

Q&A s 5:50-5:55

[5:50] Q&A

(ends 6:00 AM)

Reinforcement Learning 11 [5:00-6:00]

Oral s 5:00-5:20

[5:00] APS: Active Pretraining with Successor Features

Spotlight s 5:20-5:50

[5:20] Guided Exploration with Proximal Policy Optimization using a Single Demonstration

[5:25] Self-Paced Context Evaluation for Contextual Reinforcement Learning

[5:30] Unsupervised Skill Discovery with Bottleneck Option Learning

[5:35] TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL

[5:40] Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning

[5:45] Data-efficient Hindsight Off-policy Option Learning

Q&A s 5:50-5:55

[5:50] Q&A

(ends 6:00 AM)

Learning Theory 3 [5:00-6:00]

Oral s 5:00-5:20

[5:00] The Limits of Min-Max Optimization Algorithms: Convergence to Spurious Non-Critical Sets

Spotlight s 5:20-5:50

[5:20] Theory of Spectral Method for Union of Subspaces-Based Random Geometry Graph

[5:25] Approximating a Distribution Using Weight Queries

[5:30] Estimating $\alpha$-Rank from A Few Entries with Low Rank Matrix Completion

[5:35] Revenue-Incentive Tradeoffs in Dynamic Reserve Pricing

[5:40] Towards the Unification and Robustness of Perturbation and Gradient Based Explanations

[5:45] Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed

Q&A s 5:50-5:55

[5:50] Q&A

(ends 6:00 AM)

Optimization (Nonconvex) [5:00-6:00]

Oral s 5:00-5:20

[5:00] Optimizing persistent homology based functions

Spotlight s 5:20-5:50

[5:20] Debiasing a First-order Heuristic for Approximate Bi-level Optimization

[5:25] SMG: A Shuffling Gradient-Based Method with Momentum

[5:30] Regret Minimization in Stochastic Non-Convex Learning via a Proximal-Gradient Approach

[5:35] MARINA: Faster Non-Convex Distributed Learning with Compression

[5:40] Bilevel Optimization: Convergence Analysis and Enhanced Design

[5:45] Learning from History for Byzantine Robust Optimization

Q&A s 5:50-5:55

[5:50] Q&A

(ends 6:00 AM)

Supervised Learning 1 [5:00-6:00]

Oral s 5:00-5:20

[5:00] When All We Need is a Piece of the Pie: A Generic Framework for Optimizing Two-way Partial AUC

Spotlight s 5:20-5:50

[5:20] SiameseXML: Siamese Networks meet Extreme Classifiers with 100M Labels

[5:25] Disentangling Sampling and Labeling Bias for Learning in Large-output Spaces

[5:30] Learning Randomly Perturbed Structured Predictors for Direct Loss Minimization

[5:35] Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity

[5:40] Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?

[5:45] Meta-learning Hyperparameter Performance Prediction with Neural Processes

Q&A s 5:50-5:55

[5:50] Q&A

(ends 6:00 AM)

Probabilistic Methods 1 [5:00-6:00]

Oral s 5:00-5:20

[5:00] Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding

Spotlight s 5:20-5:50

[5:20] Sawtooth Factorial Topic Embeddings Guided Gamma Belief Network

[5:25] Kernel Continual Learning

[5:30] XOR-CD: Linearly Convergent Constrained Structure Generation

[5:35] ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables

[5:40] Composing Normalizing Flows for Inverse Problems

[5:45] Nonparametric Hamiltonian Monte Carlo

Q&A s 5:50-5:55

[5:50] Q&A

(ends 6:00 AM)

Learning Theory 2 [5:00-6:00]

Oral s 5:00-5:20

[5:00] Robust Density Estimation from Batches: The Best Things in Life are (Nearly) Free

Spotlight s 5:20-5:50

[5:20] Generalization Bounds in the Presence of Outliers: a Median-of-Means Study

[5:25] Meta Learning for Support Recovery in High-dimensional Precision Matrix Estimation

[5:30] Robust Inference for High-Dimensional Linear Models via Residual Randomization

[5:35] Don’t Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification

[5:40] Generalization Guarantees for Neural Architecture Search with Train-Validation Split

[5:45] Optimal Estimation of High Dimensional Smooth Additive Function Based on Noisy Observations

Q&A s 5:50-5:55

[5:50] Q&A

(ends 6:00 AM)

6 a.m.

Online Learning 1 [6:00-7:00]

Oral s 6:00-6:20

[6:00] Regret and Cumulative Constraint Violation Analysis for Online Convex Optimization with Long Term Constraints

Spotlight s 6:20-6:50

[6:20] Near-Optimal Confidence Sequences for Bounded Random Variables

[6:25] Joint Online Learning and Decision-making via Dual Mirror Descent

[6:30] Online A-Optimal Design and Active Linear Regression

[6:35] Fairness and Bias in Online Selection

[6:40] ChaCha for Online AutoML

[6:45] An Algorithm for Stochastic and Adversarial Bandits with Switching Costs

Q&A s 6:50-6:55

[6:50] Q&A

(ends 7:00 AM)

Algorithms and Applications [6:00-7:00]

Oral s 6:00-6:20

[6:00] Elastic Graph Neural Networks

Spotlight s 6:20-6:50

[6:20] How could Neural Networks understand Programs?

[6:25] ProGraML: A Graph-based Program Representation for Data Flow Analysis and Compiler Optimizations

[6:30] How Do Adam and Training Strategies Help BNNs Optimization

[6:35] Quantifying and Reducing Bias in Maximum Likelihood Estimation of Structured Anomalies

[6:40] Learning from Nested Data with Ornstein Auto-Encoders

[6:45] Kernel-Based Reinforcement Learning: A Finite-Time Analysis

Q&A s 6:50-6:55

[6:50] Q&A

(ends 7:00 AM)

Learning Theory 4 [6:00-7:00]

Oral s 6:00-6:20

[6:00] Agnostic Learning of Halfspaces with Gradient Descent via Soft Margins

Spotlight s 6:20-6:50

[6:20] Two-way kernel matrix puncturing: towards resource-efficient PCA and spectral clustering

[6:25] A Lower Bound for the Sample Complexity of Inverse Reinforcement Learning

[6:30] Estimation and Quantization of Expected Persistence Diagrams

[6:35] Post-selection inference with HSIC-Lasso

[6:40] Provable Robustness of Adversarial Training for Learning Halfspaces with Noise

[6:45] Distribution-Free Calibration Guarantees for Histogram Binning without Sample Splitting

Q&A s 6:50-6:55

[6:50] Q&A

(ends 7:00 AM)

Game Theory and Econ [6:00-7:00]

Oral s 6:00-6:20

[6:00] Reserve Price Optimization for First Price Auctions in Display Advertising

Spotlight s 6:20-6:50

[6:20] Align, then memorise: the dynamics of learning with feedback alignment

[6:25] Connecting Optimal Ex-Ante Collusion in Teams to Extensive-Form Correlation: Faster Algorithms and Positive Complexity Results

[6:30] Learning to Price Against a Moving Target

[6:35] Fast Algorithms for Stackelberg Prediction Game with Least Squares Loss

[6:40] Approximate Group Fairness for Clustering

[6:45] Incentivizing Compliance with Algorithmic Instruments

Q&A s 6:50-6:55

[6:50] Q&A

(ends 7:00 AM)

Reinforcement Learning Theory 1 [6:00-7:00]

Oral s 6:00-6:20

[6:00] Bilinear Classes: A Structural Framework for Provable Generalization in RL

Spotlight s 6:20-6:50

[6:20] Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning

[6:25] Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with √T Regret

[6:30] Reward Identification in Inverse Reinforcement Learning

[6:35] Online Optimization in Games via Control Theory: Connecting Regret, Passivity and Poincaré Recurrence

[6:40] Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations

[6:45] Robust Reinforcement Learning using Least Squares Policy Iteration with Provable Performance Guarantees

Q&A s 6:50-6:55

[6:50] Q&A

(ends 7:00 AM)

Reinforcement Learning and Optimization [6:00-7:00]

Oral s 6:00-6:20

[6:00] Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured Transitions

Spotlight s 6:20-6:50

[6:20] Megaverse: Simulating Embodied Agents at One Million Experiences per Second

[6:25] Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing

[6:30] Towards Open Ad Hoc Teamwork Using Graph-based Policy Learning

[6:35] Off-Belief Learning

[6:40] On Reinforcement Learning with Adversarial Corruption and Its Application to Block MDP

[6:45] Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning

Q&A s 6:50-6:55

[6:50] Q&A

(ends 7:00 AM)

Optimization and Algorithms 3 [6:00-7:00]

Oral s 6:00-6:20

[6:00] Dynamic Game Theoretic Neural Optimizer

Spotlight s 6:20-6:50

[6:20] Zero-Shot Knowledge Distillation from a Decision-Based Black-Box Model

[6:25] A Modular Analysis of Provable Acceleration via Polyak's Momentum: Training a Wide ReLU Network and a Deep Linear Network

[6:30] Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers

[6:35] Tractable structured natural-gradient descent using local parameterizations

[6:40] Towards Rigorous Interpretations: a Formalisation of Feature Attribution

[6:45] Distributed Nystr\"{o}m Kernel Learning with Communications

Q&A s 6:50-6:55

[6:50] Q&A

(ends 7:00 AM)

Reinforcement Learning 12 [6:00-7:00]

Oral s 6:00-6:20

[6:00] Model-based Reinforcement Learning for Continuous Control with Posterior Sampling

Spotlight s 6:20-6:50

[6:20] Principled Exploration via Optimistic Bootstrapping and Backward Induction

[6:25] Ensemble Bootstrapping for Q-Learning

[6:30] Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm

[6:35] A Regret Minimization Approach to Iterative Learning Control

[6:40] TempoRL: Learning When to Act

[6:45] State Relevance for Off-Policy Evaluation

Q&A s 6:50-6:55

[6:50] Q&A

(ends 7:00 AM)

Supervised Learning 2 [6:00-7:00]

Oral s 6:00-6:20

[6:00] Understanding Instance-Level Label Noise: Disparate Impacts and Treatments

Spotlight s 6:20-6:50

[6:20] Selecting Data Augmentation for Simulating Interventions

[6:25] Training Data Subset Selection for Regression with Controlled Generalization Error

[6:30] Opening the Blackbox: Accelerating Neural Differential Equations by Regularizing Internal Solver Heuristics

[6:35] Learning from Noisy Labels with No Change to the Training Process

[6:40] What does LIME really see in images?

[6:45] Narrow Margins: Classification, Margins and Fat Tails

Q&A s 6:50-6:55

[6:50] Q&A

(ends 7:00 AM)

6:40 a.m.

Affinity Workshop:

Women in Machine Learning (WiML) Un-Workshop

(ends 8:45 PM)

7 a.m.

Bandits 1 [7:00-8:00]

Oral s 7:00-7:20

[7:00] High-dimensional Experimental Design and Kernel Bandits

Spotlight s 7:20-7:50

[7:20] Dichotomous Optimistic Search to Quantify Human Perception

[7:25] Improved Confidence Bounds for the Linear Logistic Model and Applications to Bandits

[7:30] Stochastic Multi-Armed Bandits with Unrestricted Delay Distributions

[7:35] Deciding What to Learn: A Rate-Distortion Approach

[7:40] No-regret Algorithms for Capturing Events in Poisson Point Processes

[7:45] Parametric Graph for Unimodal Ranking Bandit

Q&A s 7:50-7:55

[7:50] Q&A

(ends 8:00 AM)

Reinforcement Learning 13 [7:00-8:00]

Oral s 7:00-7:40

[7:00] The Logical Options Framework

[7:20] On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game

Spotlight s 7:40-7:50

[7:40] Adversarial Option-Aware Hierarchical Imitation Learning

[7:45] Value Iteration in Continuous Actions, States and Time

Q&A s 7:50-7:55

[7:50] Q&A

(ends 8:00 AM)

Learning Theory 6 [7:00-8:00]

Oral s 7:00-7:20

[7:00] PAC-Learning for Strategic Classification

Spotlight s 7:20-7:50

[7:20] Learning from Biased Data: A Semi-Parametric Approach

[7:25] Learning in Nonzero-Sum Stochastic Games with Potentials

[7:30] Guarantees for Tuning the Step Size using a Learning-to-Learn Approach

[7:35] Large-Scale Multi-Agent Deep FBSDEs

[7:40] Multi-group Agnostic PAC Learnability

[7:45] One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning

Q&A s 7:50-7:55

[7:50] Q&A

(ends 8:00 AM)

Reinforcement Learning and Bandits [7:00-8:00]

Spotlight s 7:00-7:45

[7:00] Instabilities of Offline RL with Pre-Trained Neural Representation

[7:05] Path Planning using Neural A* Search

[7:10] Group-Sparse Matrix Factorization for Transfer Learning of Word Embeddings

[7:15] Tightening the Dependence on Horizon in the Sample Complexity of Q-Learning

[7:20] Solving Challenging Dexterous Manipulation Tasks With Trajectory Optimisation and Reinforcement Learning

[7:25] Continuous-time Model-based Reinforcement Learning

[7:30] Bayesian Optimistic Optimisation with Exponentially Decaying Regret

[7:35] Best Model Identification: A Rested Bandit Formulation

[7:40] Global Convergence of Policy Gradient for Linear-Quadratic Mean-Field Control/Game in Continuous Time

Q&A s 7:45-7:50

[7:45] Q&A

(ends 8:00 AM)

Learning Theory 5 [7:00-8:00]

Oral s 7:00-7:20

[7:00] Modelling Behavioural Diversity for Learning in Open-Ended Games

Spotlight s 7:20-7:50

[7:20] Follow-the-Regularized-Leader Routes to Chaos in Routing Games

[7:25] How to Learn when Data Reacts to Your Model: Performative Gradient Descent

[7:30] Continuous Coordination As a Realistic Scenario for Lifelong Learning

[7:35] Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games

[7:40] Collaborative Bayesian Optimization with Fair Regret

[7:45] Exponentially Many Local Minima in Quantum Neural Networks

Q&A s 7:50-7:55

[7:50] Q&A

(ends 8:00 AM)

Deep Learning Theory 3 [7:00-8:00]

Oral s 7:00-7:20

[7:00] On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent

Spotlight s 7:20-7:50

[7:20] A statistical perspective on distillation

[7:25] The Lipschitz Constant of Self-Attention

[7:30] Revealing the Structure of Deep Neural Networks via Convex Duality

[7:35] Representational aspects of depth and conditioning in normalizing flows

[7:40] Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning

[7:45] The Hintons in your Neural Network: a Quantum Field Theory View of Deep Learning

Q&A s 7:50-7:55

[7:50] Q&A

(ends 8:00 AM)

Applications (Bio) 1 [7:00-8:00]

Oral s 7:00-7:20

[7:00] Inferring Latent Dynamics Underlying Neural Population Activity via Neural Differential Equations

Spotlight s 7:20-7:50

[7:20] Learning Queueing Policies for Organ Transplantation Allocation using Interpretable Counterfactual Survival Analysis

[7:25] Deep Continuous Networks

[7:30] SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks

[7:35] Factor-analytic inverse regression for high-dimension, small-sample dimensionality reduction

[7:40] On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classification

[7:45] AGENT: A Benchmark for Core Psychological Reasoning

Q&A s 7:50-7:55

[7:50] Q&A

(ends 8:00 AM)

Time Series 1 [7:00-8:00]

Oral s 7:00-7:20

[7:00] Inferring serial correlation with dynamic backgrounds

Spotlight s 7:20-7:50

[7:20] Variance Reduced Training with Stratified Sampling for Forecasting Models

[7:25] Necessary and sufficient conditions for causal feature selection in time series with latent common causes

[7:30] Multiplying Matrices Without Multiplying

[7:35] The Power of Log-Sum-Exp: Sequential Density Ratio Matrix Estimation for Speed-Accuracy Optimization

[7:40] Data-driven Prediction of General Hamiltonian Dynamics via Learning Exactly-Symplectic Maps

[7:45] Learning Stochastic Behaviour from Aggregate Data

Q&A s 7:50-7:55

[7:50] Q&A

(ends 8:00 AM)

Kernel Methods [7:00-8:00]

Oral s 7:00-7:20

[7:00] Kernel Stein Discrepancy Descent

Spotlight s 7:20-7:50

[7:20] Conditional Distributional Treatment Effect with Kernel Conditional Mean Embeddings and U-Statistic Regression

[7:25] Generalised Lipschitz Regularisation Equals Distributional Robustness

[7:30] Interpretable Stein Goodness-of-fit Tests on Riemannian Manifold

[7:35] An exact solver for the Weston-Watkins SVM subproblem

[7:40] Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment Restriction

[7:45] Faster Kernel Matrix Algebra via Density Estimation

Q&A s 7:50-7:55

[7:50] Q&A

(ends 8:00 AM)

Sparsity and Compressed Sensing [7:00-8:00]

Oral s 7:00-7:20

[7:00] Measuring Robustness in Deep Learning Based Compressive Sensing

Spotlight s 7:20-7:50

[7:20] Instance-Optimal Compressed Sensing via Posterior Sampling

[7:25] A Nullspace Property for Subspace-Preserving Recovery

[7:30] Homomorphic Sensing: Sparsity and Noise

[7:35] Active Deep Probabilistic Subsampling

[7:40] Prior Image-Constrained Reconstruction using Style-Based Generative Models

[7:45] Intermediate Layer Optimization for Inverse Problems using Deep Generative Models

Q&A s 7:50-7:55

[7:50] Q&A

(ends 8:00 AM)

8 a.m.

Invited Talk:

Esther Duflo, Plumbers and Mechanics: How ML can complement RCT in policy experiments

Esther Duflo

(ends 9:00 AM)

9 a.m.

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

Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices

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

MARINA: Faster Non-Convex Distributed Learning with Compression

Tractable structured natural-gradient descent using local parameterizations

Towards Open Ad Hoc Teamwork Using Graph-based Policy Learning

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

The Logical Options Framework

Agnostic Learning of Halfspaces with Gradient Descent via Soft Margins

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

Prior Image-Constrained Reconstruction using Style-Based Generative Models

Joint Online Learning and Decision-making via Dual Mirror Descent

Path Planning using Neural A* Search

TempoRL: Learning When to Act

A statistical perspective on distillation

Bilinear Classes: A Structural Framework for Provable Generalization in RL

Self-Paced Context Evaluation for Contextual Reinforcement Learning

How Do Adam and Training Strategies Help BNNs Optimization

Near Optimal Reward-Free Reinforcement Learning

Quantifying and Reducing Bias in Maximum Likelihood Estimation of Structured Anomalies

Dynamic Game Theoretic Neural Optimizer

Group-Sparse Matrix Factorization for Transfer Learning of Word Embeddings

An exact solver for the Weston-Watkins SVM subproblem

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

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

Kernel Stein Discrepancy Descent

AGENT: A Benchmark for Core Psychological Reasoning

Active Feature Acquisition with Generative Surrogate Models

Generalised Lipschitz Regularisation Equals Distributional Robustness

Approximating a Distribution Using Weight Queries

Learning from History for Byzantine Robust Optimization

A Regret Minimization Approach to Iterative Learning Control

Distribution-Free Calibration Guarantees for Histogram Binning without Sample Splitting

Instance-Optimal Compressed Sensing via Posterior Sampling

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

Continuous Coordination As a Realistic Scenario for Lifelong Learning

Sawtooth Factorial Topic Embeddings Guided Gamma Belief Network

Batch Value-function Approximation with Only Realizability

Revealing the Structure of Deep Neural Networks via Convex Duality

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

Spectral Normalisation for Deep Reinforcement Learning: An Optimisation Perspective

Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning

Learning Randomly Perturbed Structured Predictors for Direct Loss Minimization

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

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

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

Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning

Ensemble Bootstrapping for Q-Learning

APS: Active Pretraining with Successor Features

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

Fairness and Bias in Online Selection

SMG: A Shuffling Gradient-Based Method with Momentum

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

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

Megaverse: Simulating Embodied Agents at One Million Experiences per Second

Interpretable Stein Goodness-of-fit Tests on Riemannian Manifold

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

Deep Continuous Networks

Best Model Identification: A Rested Bandit Formulation

Towards Rigorous Interpretations: a Formalisation of Feature Attribution

Intermediate Layer Optimization for Inverse Problems using Deep Generative Models

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

Elastic Graph Neural Networks

On Energy-Based Models with Overparametrized Shallow Neural Networks

TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL

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

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

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

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

Bilevel Optimization: Convergence Analysis and Enhanced Design

Selecting Data Augmentation for Simulating Interventions

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

Reward Identification in Inverse Reinforcement Learning

Post-selection inference with HSIC-Lasso

Principled Exploration via Optimistic Bootstrapping and Backward Induction

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

Incentivizing Compliance with Algorithmic Instruments

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

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

A Lower Bound for the Sample Complexity of Inverse Reinforcement Learning

Robust Inference for High-Dimensional Linear Models via Residual Randomization

Collaborative Bayesian Optimization with Fair Regret

State Relevance for Off-Policy Evaluation

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

Nonparametric Hamiltonian Monte Carlo

Multi-group Agnostic PAC Learnability

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

Exponentially Many Local Minima in Quantum Neural Networks

Solving Challenging Dexterous Manipulation Tasks With Trajectory Optimisation and Reinforcement Learning

Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations

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

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

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

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

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

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

Optimizing persistent homology based functions

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

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

Reserve Price Optimization for First Price Auctions in Display Advertising

What does LIME really see in images?

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

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

PAC-Learning for Strategic Classification

Variance Reduced Training with Stratified Sampling for Forecasting Models

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

Unsupervised Skill Discovery with Bottleneck Option Learning

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

Representational aspects of depth and conditioning in normalizing flows

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

Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers

Training Data Subset Selection for Regression with Controlled Generalization Error

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

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

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

Near-Optimal Confidence Sequences for Bounded Random Variables

No-regret Algorithms for Capturing Events in Poisson Point Processes

Meta-learning Hyperparameter Performance Prediction with Neural Processes

Fast Algorithms for Stackelberg Prediction Game with Least Squares Loss

Provable Robustness of Adversarial Training for Learning Halfspaces with Noise

Learning Stochastic Behaviour from Aggregate Data

Functional Space Analysis of Local GAN Convergence

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

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

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

Instabilities of Offline RL with Pre-Trained Neural Representation

A Nullspace Property for Subspace-Preserving Recovery

Understanding Instance-Level Label Noise: Disparate Impacts and Treatments

Kernel-Based Reinforcement Learning: A Finite-Time Analysis

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

Active Deep Probabilistic Subsampling

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

Revenue-Incentive Tradeoffs in Dynamic Reserve Pricing

Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity

Stochastic Multi-Armed Bandits with Unrestricted Delay Distributions

High-dimensional Experimental Design and Kernel Bandits

Relative Deviation Margin Bounds

Deciding What to Learn: A Rate-Distortion Approach

The Lipschitz Constant of Self-Attention

Generalization Guarantees for Neural Architecture Search with Train-Validation Split

Model-based Reinforcement Learning for Continuous Control with Posterior Sampling

Narrow Margins: Classification, Margins and Fat Tails

Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding

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

ChaCha for Online AutoML

Online A-Optimal Design and Active Linear Regression

Spectral vertex sparsifiers and pair-wise spanners over distributed graphs

XOR-CD: Linearly Convergent Constrained Structure Generation

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

Value Iteration in Continuous Actions, States and Time

Characterizing the Gap Between Actor-Critic and Policy Gradient

Approximate Group Fairness for Clustering

Learning in Nonzero-Sum Stochastic Games with Potentials

Towards the Unification and Robustness of Perturbation and Gradient Based Explanations

Estimation and Quantization of Expected Persistence Diagrams

Large-Scale Multi-Agent Deep FBSDEs

Bayesian Optimistic Optimisation with Exponentially Decaying Regret

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

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

Parametric Graph for Unimodal Ranking Bandit

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

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

SiameseXML: Siamese Networks meet Extreme Classifiers with 100M Labels

Modelling Behavioural Diversity for Learning in Open-Ended Games

Accelerating Safe Reinforcement Learning with Constraint-mismatched Baseline Policies

Homomorphic Sensing: Sparsity and Noise

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

Dichotomous Optimistic Search to Quantify Human Perception

Learning from Biased Data: A Semi-Parametric Approach

An Algorithm for Stochastic and Adversarial Bandits with Switching Costs

Measuring Robustness in Deep Learning Based Compressive Sensing

Adversarial Combinatorial Bandits with General Non-linear Reward Functions

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

Faster Kernel Matrix Algebra via Density Estimation

Learning from Noisy Labels with No Change to the Training Process

Off-Belief Learning

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

How could Neural Networks understand Programs?

Learning from Nested Data with Ornstein Auto-Encoders

Inferring serial correlation with dynamic backgrounds

Uncertainty Principles of Encoding GANs

Composing Normalizing Flows for Inverse Problems

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

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

Cross-domain Imitation from Observations

Bootstrapping Fitted Q-Evaluation for Off-Policy Inference

Adversarial Option-Aware Hierarchical Imitation Learning

Continuous-time Model-based Reinforcement Learning

Guided Exploration with Proximal Policy Optimization using a Single Demonstration

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

Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing

Multiplying Matrices Without Multiplying

Inferring Latent Dynamics Underlying Neural Population Activity via Neural Differential Equations

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

Kernel Continual Learning

Data-efficient Hindsight Off-policy Option Learning

Learning to Price Against a Moving Target

(ends 11:00 AM)

1 p.m.

3:30 p.m.

5 p.m.

Learning Theory 7 [5:00-6:00]

Oral s 5:00-5:20

[5:00] Learning Optimal Auctions with Correlated Valuations from Samples

Spotlight s 5:20-5:50

[5:20] Alternative Microfoundations for Strategic Classification

[5:25] Multi-Receiver Online Bayesian Persuasion

[5:30] Online Learning for Load Balancing of Unknown Monotone Resource Allocation Games

[5:35] Compressed Maximum Likelihood

[5:40] Consistent regression when oblivious outliers overwhelm

[5:45] Asymptotics of Ridge Regression in Convolutional Models

Q&A s 5:50-5:55

[5:50] Q&A

(ends 6:00 PM)

Learning Theory 8 [5:00-6:00]