ICML 2022

Search Schedule »

Search:

Session:

Event type:

Hide breaks and receptions:

Day:

Show All »

July 17, 2022 Expo schedule » New in ML »

Timezone: America/New_York »

Indicates the beginning of a session

Time	Room 309	Room 310	Ballroom 3	Room 307	Virtual	Ballroom 1	Room 301	Charles Street Lobby and Hall B	Pratt St. Lobby
Sun Jul 17, 2022
09:00 AM (Socials)					Building NLP for African Languages
10:00 AM (Registration Desks)									Registration Check-in Desk
12:00 PM (Expo Demonstrations, Expo Talk Panels, Expo Workshops)	Enabling Hand Gesture Customization on Wrist-Worn Devices	AEPsych: active learning for human perception and preferences TorchRL: the PyTorch RL Domain library	Challenges Of Applying Graph Neural Networks				Real World RL with Vowpal Wabbit and Azure Personalizer
12:30 PM (Expo Talk Panels)						Knowledge graph-based recommendation framework identifies drivers of resistance in EGFR mutant non-small cell lung cancer
01:20 PM (Expo Demonstrations)						Creating a scalable, reproducible, and reliable environment for model development with AstraZeneca and W&B.
02:00 PM (Expo Demonstrations, Expo Talk Panels)	Enabling Hand Gesture Customization on Wrist-Worn Devices			Amazon SageMaker Model Parallelism: A General and Flexible Framework for Large Model Training
02:30 PM (Expo Talk Panels)						Machine learning for drug discovery: Challenges and opportunities
03:15 PM (Expo Demonstrations)				Robust and Fast Detection of Toxic Speech Content via Machine Learning
04:15 PM (Expo Talk Panels)						Towards Robust Waveform-Based Acoustic Models
05:30 PM (Receptions)								Opening Reception

Time	Hall F	Room 301 - 303	Room 310	Room 307	Hall G	Virtual	Ballroom 1 & 2	Ballroom 3 & 4
Mon Jul 18, 2022
08:00 AM (Affinity Workshops)								LatinX in AI (LXAI) LXAI Research Workshop
08:30 AM (Affinity Workshops)					Women in Machine Learning (WiML) Un-Workshop
09:00 AM (Affinity Workshops)		New In Machine Learning (NewInML)
09:30 AM (Tutorials)	Causality and Deep Learning: Synergies, Challenges and the Future			Validity, Reliability, and Significance: A Tutorial on Statistical Methods for Reproducible Machine Learning			Quantitative Reasoning About Data Privacy in Machine Learning
11:00 AM (Socials)						Oxford Womn in Computer Science: Highlighting Womn Researchers in ML
01:00 PM (Socials, Tutorials)	Learning for Interactive Agents			Climate Change and Machine Learning: Opportunities, Challenges, and Considerations		How to Negotiate Industry Offers in AI	Bridging Learning and Decision Making
02:00 PM (Socials)						It’s all about Transformers!
03:30 PM (Tutorials)	Welcome to the "Big Model" Era: Techniques and Systems to Train and Serve Bigger Models			Causal Fairness Analysis			Sampling as First-Order Optimization over a space of probability measures
07:00 PM (Socials)			Quantum ML	Designing an RL system toward AGI

Time	Hall F	Room 327 - 329	Room 301 - 303	Room 309	Room 318 - 320	Room 310	Room 307	Hall G	Virtual	Ballroom 1 & 2	Hall E	Ballroom 3 & 4
Tue Jul 19, 2022
08:45 AM (Remarkss)	Welcome by Chairs
09:00 AM (Invited Talks)	Towards a Mathematical Theory of Machine Learning
10:30 AM (Orals, Spotlights)	Reinforcement Learning Dynamic Regret of Online Markov Decision Processes	Deep Learning Structural Entropy Guided Graph Hierarchical Pooling	APP: Language, Speech and Dialog Certified Robustness Against Natural Language Attacks by Causal Intervention	Theory: Online Learning/Bandits Online Learning for Min Sum Set Cover and Pandora’s Box	Transfer/Multitask/Meta Learning Multi-Task Learning as a Bargaining Game	Deep Learning: Generative Models/Autoencoders Exploring and Exploiting Hubness Priors for High-Quality GAN Latent Sampling	Optimization: Convex Exact Optimal Accelerated Complexity for Fixed-Point Iterations	Deep Learning: Robustness Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Them		Social Aspects Differentially Private Approximate Quantiles		Probabilistic Methods/Applications Tackling covariate shift with node-based Bayesian neural networks
10:35 AM (Spotlights)	On the Impossibility of Learning to Cooperate with Adaptive Partner Strategies in Repeated Games	Self-Supervised Representation Learning via Latent Graph Prediction	A$^3$T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing		Frustratingly Easy Transferability Estimation	ButterflyFlow: Building Invertible Layers with Butterfly Matrices				Fairness Interventions as (Dis)Incentives for Strategic Manipulation
10:40 AM (Spotlights)	Distributional Hamilton-Jacobi-Bellman Equations for Continuous-Time Reinforcement Learning	DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting	On the Learning of Non-Autoregressive Transformers		Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling	Controlling Conditional Language Models without Catastrophic Forgetting				Robust Models Are More Interpretable Because Attributions Look Normal
10:45 AM (Spotlights)	Provable Reinforcement Learning with a Short-Term Memory	Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets	Latent Diffusion Energy-Based Model for Interpretable Text Modelling		A Difference Standardization Method for Mutual Transfer Learning	GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models				Sequential Covariate Shift Detection Using Classifier Two-Sample Tests
10:50 AM (Spotlights)	Optimistic Linear Support and Successor Features as a Basis for Optimal Policy Transfer	Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning	UNIREX: A Unified Learning Framework for Language Model Rationale Extraction	Smoothed Adversarial Linear Contextual Bandits with Knapsacks	Improving Task-free Continual Learning by Distributionally Robust Memory Evolution	Structure-preserving GANs	Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions	ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks		A Joint Exponential Mechanism For Differentially Private Top-$k$		Why the Rich Get Richer? On the Balancedness of Random Partition Models
10:55 AM (Spotlights)	Mirror Learning: A Unifying Framework of Policy Optimisation	Analyzing and Mitigating Interference in Neural Architecture Search	Black-Box Tuning for Language-Model-as-a-Service	Simultaneously Learning Stochastic and Adversarial Bandits with General Graph Feedback	A Multi-objective / Multi-task Learning Framework Induced by Pareto Stationarity	DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale	NysADMM: faster composite convex optimization via low-rank approximation	Provably Adversarially Robust Nearest Prototype Classifiers		Transfer Learning In Differential Privacy's Hybrid-Model		A Completely Tuning-Free and Robust Approach to Sparse Precision Matrix Estimation
11:00 AM (Orals, Spotlights)	Improved No-Regret Algorithms for Stochastic Shortest Path with Linear MDP	Reverse Engineering $\ell_p$ attacks: A block-sparse optimization approach with recovery guarantees	Understanding Dataset Difficulty with $\mathcal{V}$-Usable Information	Thompson Sampling for (Combinatorial) Pure Exploration	Sparse Invariant Risk Minimization	Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Models	FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated Learning	Certifying Out-of-Domain Generalization for Blackbox Functions		Robust Kernel Density Estimation with Median-of-Means principle		Markov Chain Monte Carlo for Continuous-Time Switching Dynamical Systems
11:05 AM (Orals, Spotlights)		Unified Scaling Laws for Routed Language Models		Revisiting Online Submodular Minimization: Gap-Dependent Regret Bounds, Best of Both Worlds and Adversarial Robustness	Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning	Equivariant Diffusion for Molecule Generation in 3D	Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers	Intriguing Properties of Input-Dependent Randomized Smoothing		Bounding Training Data Reconstruction in Private (Deep) Learning		Calibrated Learning to Defer with One-vs-All Classifiers
11:10 AM (Orals, Spotlights)				Rotting Infinitely Many-Armed Bandits			Pairwise Conditional Gradients without Swap Steps and Sparser Kernel Herding	To Smooth or Not? When Label Smoothing Meets Noisy Labels				Tractable Uncertainty for Structure Learning
11:15 AM (Orals)				Batched Dueling Bandits			Continuous-Time Analysis of Accelerated Gradient Methods via Conservation Laws in Dilated Coordinate Systems
11:20 AM (Spotlights)	Learning Infinite-horizon Average-reward Markov Decision Process with Constraints		Co-training Improves Prompt-based Learning for Large Language Models
11:25 AM (Spotlights)	A State-Distribution Matching Approach to Non-Episodic Reinforcement Learning	DRAGONN: Distributed Randomized Approximate Gradients of Neural Networks	Directed Acyclic Transformer for Non-Autoregressive Machine Translation		A Closer Look at Smoothness in Domain Adversarial Training	Forward Operator Estimation in Generative Models with Kernel Transfer Operators				Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks
11:30 AM (Spotlights)	Langevin Monte Carlo for Contextual Bandits	A deep convolutional neural network that is invariant to time rescaling	StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models		Balancing Discriminability and Transferability for Source-Free Domain Adaptation	Conditional GANs with Auxiliary Discriminative Classifier		Evaluating the Adversarial Robustness of Adaptive Test-time Defenses		FriendlyCore: Practical Differentially Private Aggregation		DNA: Domain Generalization with Diversified Neural Averaging
11:35 AM (Spotlights)	Prompting Decision Transformer for Few-Shot Policy Generalization	LyaNet: A Lyapunov Framework for Training Neural ODEs	Unsupervised Detection of Contextualized Embedding Bias with Application to Ideology	Equivalence Analysis between Counterfactual Regret Minimization and Online Mirror Descent	Model Agnostic Sample Reweighting for Out-of-Distribution Learning	Improved StyleGAN-v2 based Inversion for Out-of-Distribution Images	Only tails matter: Average-Case Universality and Robustness in the Convex Regime	On the Generalization Analysis of Adversarial Learning		ViT-NeT: Interpretable Vision Transformers with Neural Tree Decoder		Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces
11:40 AM (Spotlights)	Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning	Transfer and Marginalize: Explaining Away Label Noise with Privileged Information	Generative Cooperative Networks for Natural Language Generation	Consistent Polyhedral Surrogates for Top-k Classification and Variants	Zero-shot AutoML with Pretrained Models	Matching Normalizing Flows and Probability Paths on Manifolds	Batch Greenkhorn Algorithm for Entropic-Regularized Multimarginal Optimal Transport: Linear Rate of Convergence and Iteration Complexity	Demystifying the Adversarial Robustness of Random Transformation Defenses		Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification		DynaMixer: A Vision MLP Architecture with Dynamic Mixing
11:45 AM (Spotlights)	Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation	On Collective Robustness of Bagging Against Data Poisoning	What Language Model Architecture and Pretraining Objective Works Best for Zero-Shot Generalization?	Stochastic Contextual Dueling Bandits under Linear Stochastic Transitivity Models	Efficient Variance Reduction for Meta-learning	Marginal Distribution Adaptation for Discrete Sets via Module-Oriented Divergence Minimization	Approximate Frank-Wolfe Algorithms over Graph-structured Support Sets	Double Sampling Randomized Smoothing		Public Data-Assisted Mirror Descent for Private Model Training		Channel Importance Matters in Few-Shot Image Classification
11:50 AM (Spotlights)		Hindering Adversarial Attacks with Implicit Neural Representations	Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding	Optimal and Efficient Dynamic Regret Algorithms for Non-Stationary Dueling Bandits	Generalizing to Evolving Domains with Latent Structure-Aware Sequential Autoencoder	Learning to Incorporate Texture Saliency Adaptive Attention to Image Cartoonization	Neural Fisher Discriminant Analysis: Optimal Neural Network Embeddings in Polynomial Time	TPC: Transformation-Specific Smoothing for Point Cloud Models		Low-Complexity Deep Convolutional Neural Networks on Fully Homomorphic Encryption Using Multiplexed Parallel Convolutions		Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization
11:55 AM (Spotlights)		From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model	ROCK: Causal Inference Principles for Reasoning about Commonsense Causality	Online Nonsubmodular Minimization with Delayed Costs: From Full Information to Bandit Feedback	Partial disentanglement for domain adaptation	Region-Based Semantic Factorization in GANs	Active Sampling for Min-Max Fairness			Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic Data
01:30 PM (Orals, Spotlights)	APP: Computer Vision Robust Group Synchronization via Quadratic Programming	DL: Graph Neural Networks pathGCN: Learning General Graph Spatial Operators from Paths	MISC: Unsupervised and Semi-supervised Learning An iterative clustering algorithm for the Contextual Stochastic Block Model with optimality guarantees	Reinforcement Learning: Deep/Batch/Offline Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution	Optimization Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning	Theory: Bandits/RL/Everything Else Robustness Implies Generalization via Data-Dependent Generalization Bounds	PM: Gaussian Processes Additive Gaussian Processes Revisited	Theory Learning Mixtures of Linear Dynamical Systems		DL: Algorithms Online Continual Learning through Mutual Information Maximization		SA: Accountability, Transparency and Interpretability Meaningfully debugging model mistakes using conceptual counterfactual explanations
01:35 PM (Spotlights)	UAST: Uncertainty-Aware Siamese Tracking	Graph-Coupled Oscillator Networks	Smoothed Adaptive Weighting for Imbalanced Semi-Supervised Learning: Improve Reliability Against Unknown Distribution Data				Probabilistic ODE Solutions in Millions of Dimensions			Learning Iterative Reasoning through Energy Minimization		Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments
01:40 PM (Spotlights)	You Only Cut Once: Boosting Data Augmentation with a Single Cut	HousE: Knowledge Graph Embedding with Householder Parameterization	Class-Imbalanced Semi-Supervised Learning with Adaptive Thresholding				Adaptive Gaussian Process Change Point Detection			DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks		Robust Counterfactual Explanations for Tree-Based Ensembles
01:45 PM (Spotlights)	Generative Modeling for Multi-task Visual Learning	Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism					Volatility Based Kernels and Moving Average Means for Accurate Forecasting with Gaussian Processes			PoF: Post-Training of Feature Extractor for Improving Generalization		A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributions
01:50 PM (Spotlights)	HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning	ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning	Meta-Learning Hypothesis Spaces for Sequential Decision-making	AnyMorph: Learning Transferable Polices By Inferring Agent Morphology	Stochastic Reweighted Gradient Descent	Learning to Hash Robustly, Guaranteed	Fenrir: Physics-Enhanced Regression for Initial Value Problems	Massively Parallel $k$-Means Clustering for Perturbation Resilient Instances		Improving Ensemble Distillation With Weight Averaging and Diversifying Perturbation		Estimating and Penalizing Induced Preference Shifts in Recommender Systems
01:55 PM (Spotlights)	Parametric Visual Program Induction with Function Modularization	G$^2$CN: Graph Gaussian Convolution Networks with Concentrated Graph Filters	A Tighter Analysis of Spectral Clustering, and Beyond	DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations	Sharpened Quasi-Newton Methods: Faster Superlinear Rate and Larger Local Convergence Neighborhood	Policy Gradient Method For Robust Reinforcement Learning	Variational nearest neighbor Gaussian process	Residual-Based Sampling for Online Outlier-Robust PCA		Set Based Stochastic Subsampling		Framework for Evaluating Faithfulness of Local Explanations
02:00 PM (Orals, Socials, Spotlights)	Path-Gradient Estimators for Continuous Normalizing Flows	SpeqNets: Sparsity-aware permutation-equivariant graph networks	Online Active Regression	Stabilizing Off-Policy Deep Reinforcement Learning from Pixels	Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging	A query-optimal algorithm for finding counterfactuals	Preconditioning for Scalable Gaussian Process Hyperparameter Optimization	Scaling Gaussian Process Optimization by Evaluating a Few Unique Candidates Multiple Times	Can AI Be Used to Reduce Black Maternal Mortality?	Monarch: Expressive Structured Matrices for Efficient and Accurate Training		A Consistent and Efficient Evaluation Strategy for Attribution Methods
02:05 PM (Orals, Spotlights)		data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language		Influence-Augmented Local Simulators: a Scalable Solution for Fast Deep RL in Large Networked Systems	FedNL: Making Newton-Type Methods Applicable to Federated Learning	Linear Bandit Algorithms with Sublinear Time Complexity		Streaming Algorithms for Support-Aware Histograms				Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect Four
02:10 PM (Orals, Spotlights)				CtrlFormer: Learning Transferable State Representation for Visual Control via Transformer	Solving Stackelberg Prediction Game with Least Squares Loss via Spherically Constrained Least Squares Reformulation	Quantum-Inspired Algorithms from Randomized Numerical Linear Algebra		Power-Law Escape Rate of SGD
02:15 PM (Orals)				Offline RL Policies Should Be Trained to be Adaptive		Individual Preference Stability for Clustering		Generalized Results for the Existence and Consistency of the MLE in the Bradley-Terry-Luce Model
02:20 PM (Spotlights)	Variational Feature Pyramid Networks		On Finite-Sample Identifiability of Contrastive Learning-Based Nonlinear Independent Component Analysis				Spectral Representation of Robustness Measures for Optimization Under Input Uncertainty			Generalizing to New Physical Systems via Context-Informed Dynamics Model
02:25 PM (Spotlights)	Deep Neural Network Fusion via Graph Matching with Applications to Model Ensemble and Federated Learning	Position Prediction as an Effective Pretraining Strategy	Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis: an Integrated Framework				Bayesian Optimization under Stochastic Delayed Feedback			Self-conditioning Pre-Trained Language Models		Label-Descriptive Patterns and Their Application to Characterizing Classification Errors
02:30 PM (Spotlights)	VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix	Orchestra: Unsupervised Federated Learning via Globally Consistent Clustering	Open-Sampling: Exploring Out-of-Distribution data for Re-balancing Long-tailed datasets		Dimension-free Complexity Bounds for High-order Nonconvex Finite-sum Optimization		Bayesian Optimization for Distributionally Robust Chance-constrained Problem			TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classification		XAI for Transformers: Better Explanations through Conservative Propagation
02:35 PM (Spotlights)	Neural Implicit Dictionary Learning via Mixture-of-Expert Training	Deep and Flexible Graph Neural Architecture Search	Confidence Score for Source-Free Unsupervised Domain Adaptation	Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control	Value Function based Difference-of-Convex Algorithm for Bilevel Hyperparameter Selection Problems	Correlated Quantization for Distributed Mean Estimation and Optimization	Efficient Distributionally Robust Bayesian Optimization with Worst-case Sensitivity	Faster Algorithms for Learning Convex Functions		Bitwidth Heterogeneous Federated Learning with Progressive Weight Dequantization		Quantification and Analysis of Layer-wise and Pixel-wise Information Discarding
02:40 PM (Spotlights)	Time Is MattEr: Temporal Self-supervision for Video Transformers	GNNRank: Learning Global Rankings from Pairwise Comparisons via Directed Graph Neural Networks	Gradient Based Clustering	PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration	Probabilistic Bilevel Coreset Selection	Multiple-Play Stochastic Bandits with Shareable Finite-Capacity Arms	Improved Convergence Rates for Sparse Approximation Methods in Kernel-Based Learning	Feature selection using e-values		Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning		Interpretable Off-Policy Learning via Hyperbox Search
02:45 PM (Spotlights)	Benchmarking and Analyzing Point Cloud Classification under Corruptions	Large-Scale Graph Neural Architecture Search	Global Optimization of K-Center Clustering	Supervised Off-Policy Ranking	Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costs	Coordinated Attacks against Contextual Bandits: Fundamental Limits and Defense Mechanisms	Scalable First-Order Bayesian Optimization via Structured Automatic Differentiation	ActiveHedge: Hedge meets Active Learning		Knowledge Base Question Answering by Case-based Reasoning over Subgraphs		Neuron Dependency Graphs: A Causal Abstraction of Neural Networks
02:50 PM (Spotlights)	Understanding The Robustness in Vision Transformers	Optimization-Induced Graph Implicit Nonlinear Diffusion	Latent Outlier Exposure for Anomaly Detection with Contaminated Data	The Primacy Bias in Deep Reinforcement Learning	On Implicit Bias in Overparameterized Bilevel Optimization	The Algebraic Path Problem for Graph Metrics		One-Pass Algorithms for MAP Inference of Nonsymmetric Determinantal Point Processes		When AUC meets DRO: Optimizing Partial AUC for Deep Learning with Non-Convex Convergence Guarantee		On the Adversarial Robustness of Causal Algorithmic Recourse
02:55 PM (Spotlights)				Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning		Steerable 3D Spherical Neurons		Deciphering Lasso-based Classification Through a Large Dimensional Analysis of the Iterative Soft-Thresholding Algorithm				Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations
04:15 PM (Orals, Spotlights)	SA: Trustworthy Machine Learning POEM: Out-of-Distribution Detection with Posterior Sampling	DL: Sequential Models Modeling Irregular Time Series with Continuous Recurrent Units	APP: Neuroscience, Cognitive Science Bayesian Nonparametric Learning for Point Processes with Spatial Homogeneity: A Spatial Analysis of NBA Shot Locations	OPT: Non-Convex Neural Network Weights Do Not Converge to Stationary Points: An Invariant Measure Perspective	RL: Multi-agent Model-Free Opponent Shaping	Theory Cooperative Online Learning in Stochastic and Adversarial MDPs	PM: Monte Carlo and Sampling Methods Scalable MCMC Sampling for Nonsymmetric Determinantal Point Processes	T: Learning/Deep Learning Theory H-Consistency Bounds for Surrogate Loss Minimizers		Deep Learning Prototype Based Classification from Hierarchy to Fairness		MISC: Causality Coordinated Double Machine Learning
04:20 PM (Spotlights)		TACTiS: Transformer-Attentional Copulas for Time Series	On the Effects of Artificial Data Modification	Convergence and Recovery Guarantees of the K-Subspaces Method for Subspace Clustering	Pessimism meets VCG: Learning Dynamic Mechanism Design via Offline Reinforcement Learning					Neural-Symbolic Models for Logical Queries on Knowledge Graphs		Exploiting Independent Instruments: Identification and Distribution Generalization
04:25 PM (Spotlights)		CerDEQ: Certifiable Deep Equilibrium Model	Deep Squared Euclidean Approximation to the Levenshtein Distance for DNA Storage	Restarted Nonconvex Accelerated Gradient Descent: No More Polylogarithmic Factor in the $O(\epsilon^{-7/4})$ Complexity	Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium Computation					Deep Probability Estimation		Partial Counterfactual Identification from Observational and Experimental Data
04:30 PM (Spotlights)		Approximately Equivariant Networks for Imperfectly Symmetric Dynamics	How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models	Understanding the unstable convergence of gradient descent	Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning					Uncertainty Modeling in Generative Compressed Sensing		On Measuring Causal Contributions via do-interventions
04:35 PM (Spotlights)	Selective Network Linearization for Efficient Private Inference	IDYNO: Learning Nonparametric DAGs from Interventional Dynamic Data	Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass	Federated Minimax Optimization: Improved Convergence Analyses and Algorithms	Scalable Deep Reinforcement Learning Algorithms for Mean Field Games	Simple and near-optimal algorithms for hidden stratification and multi-group learning	Robust SDE-Based Variational Formulations for Solving Linear PDEs via Deep Learning	Learning General Halfspaces with Adversarial Label Noise via Online Gradient Descent		Going Deeper into Permutation-Sensitive Graph Neural Networks		The Role of Deconfounding in Meta-learning
04:40 PM (Spotlights)	Efficient Computation of Higher-Order Subgraph Attribution via Message Passing	GSmooth: Certified Robustness against Semantic Transformations via Generalized Randomized Smoothing	How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspective	Inductive Matrix Completion: No Bad Local Minima and a Fast Algorithm	Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning	Being Properly Improper	Hessian-Free High-Resolution Nesterov Acceleration For Sampling	The Teaching Dimension of Regularized Kernel Learners		Learning from Counterfactual Links for Link Prediction		CITRIS: Causal Identifiability from Temporal Intervened Sequences
04:45 PM (Orals, Spotlights)	A Theoretical Analysis on Independence-driven Importance Weighting for Covariate-shift Generalization	Neural Laplace: Learning diverse classes of differential equations in the Laplace domain	Contrastive Mixture of Posteriors for Counterfactual Inference, Data Integration and Fairness	FedNest: Federated Bilevel, Minimax, and Compositional Optimization	Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence	Neural Network Pruning Denoises the Features and Makes Local Connectivity Emerge in Visual Tasks	LSB: Local Self-Balancing MCMC in Discrete Spaces	Sparse Mixed Linear Regression with Guarantees: Taming an Intractable Problem with Invex Relaxation		Training Discrete Deep Generative Models via Gapped Straight-Through Estimator		Online Balanced Experimental Design
04:50 PM (Orals, Spotlights)	Modular Conformal Calibration					On the Finite-Time Complexity and Practical Computation of Approximate Stationarity Concepts of Lipschitz Functions	A Langevin-like Sampler for Discrete Distributions	TURF: Two-Factor, Universal, Robust, Fast Distribution Learning Algorithm		Correct-N-Contrast: a Contrastive Approach for Improving Robustness to Spurious Correlations		Minimum Cost Intervention Design for Causal Effect Identification
04:55 PM (Orals, Spotlights)	Rethinking Image-Scaling Attacks: The Interplay Between Vulnerabilities in Machine Learning Systems					Nearly Optimal Policy Optimization with Stable at Any Time Guarantee	Scalable Spike-and-Slab	Multiclass learning with margin: exponential rates with no bias-variance trade-off
05:00 PM (Orals)						Contextual Bandits with Smooth Regret: Efficient Learning in Continuous Action Spaces	Nonparametric Involutive Markov Chain Monte Carlo	Refined Convergence Rates for Maximum Likelihood Estimation under Finite Mixture Models
05:05 PM (Spotlights)		Improving Language Models by Retrieving from Trillions of Tokens	Describing Differences between Text Distributions with Natural Language	AdaGrad Avoids Saddle Points	Self-Organized Polynomial-Time Coordination Graphs
05:10 PM (Spotlights)		Closed-Form Diffeomorphic Transformations for Time Series Alignment	Distinguishing rule- and exemplar-based generalization in learning systems	Fast and Provable Nonconvex Tensor RPCA	Individual Reward Assisted Multi-Agent Reinforcement Learning					Principal Component Flows		Causal structure-based root cause analysis of outliers
05:15 PM (Spotlights)	Context-Aware Drift Detection	Removing Batch Normalization Boosts Adversarial Training	Burst-Dependent Plasticity and Dendritic Amplification Support Target-Based Learning and Hierarchical Imitation Learning	On Convergence of Gradient Descent Ascent: A Tight Local Analysis	Generalized Beliefs for Cooperative AI					Bit Prioritization in Variational Autoencoders via Progressive Coding		Instrumental Variable Regression with Confounder Balancing
05:20 PM (Spotlights)	Accelerating Shapley Explanation via Contributive Cooperator Selection	Forget-free Continual Learning with Winning Subnetworks	A Deep Learning Approach for the Segmentation of Electroencephalography Data in Eye Tracking Applications	Convergence Rates of Non-Convex Stochastic Gradient Descent Under a Generic Lojasiewicz Condition and Local Smoothness	Greedy when Sure and Conservative when Uncertain about the Opponents	Minimax M-estimation under Adversarial Contamination	Continual Repeated Annealed Flow Transport Monte Carlo	High Probability Guarantees for Nonconvex Stochastic Gradient Descent with Heavy Tails		Generative Flow Networks for Discrete Probabilistic Modeling		Causal Transformer for Estimating Counterfactual Outcomes
05:25 PM (Spotlights)	An Equivalence Between Data Poisoning and Byzantine Gradient Attacks	FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting	Minimizing Control for Credit Assignment with Strong Feedback	A Single-Loop Gradient Descent and Perturbed Ascent Algorithm for Nonconvex Functional Constrained Optimization	Deconfounded Value Decomposition for Multi-Agent Reinforcement Learning	Adaptive Best-of-Both-Worlds Algorithm for Heavy-Tailed Multi-Armed Bandits	Algorithms for the Communication of Samples	An Initial Alignment between Neural Network and Target is Needed for Gradient Descent to Learn		Diffusion bridges vector quantized variational autoencoders		Causal Inference Through the Structural Causal Marginal Problem
05:30 PM (Spotlights)	DAVINZ: Data Valuation using Deep Neural Networks at Initialization	Adversarial Robustness against Multiple and Single $l_p$-Threat Models via Quick Fine-Tuning of Robust Classifiers	Self-Supervised Models of Audio Effectively Explain Human Cortical Responses to Speech	Anticorrelated Noise Injection for Improved Generalization	Welfare Maximization in Competitive Equilibrium: Reinforcement Learning for Markov Exchange Economy	Efficiently Learning the Topology and Behavior of a Networked Dynamical System Via Active Queries	Low-Precision Stochastic Gradient Langevin Dynamics	Inductive Biases and Variable Creation in Self-Attention Mechanisms		Mitigating Modality Collapse in Multimodal VAEs via Impartial Optimization		Functional Generalized Empirical Likelihood Estimation for Conditional Moment Restrictions
05:35 PM (Spotlights)	Sample Efficient Learning of Predictors that Complement Humans	On the Practicality of Deterministic Epistemic Uncertainty	Towards Scaling Difference Target Propagation by Learning Backprop Targets		Simplex Neural Population Learning: Any-Mixture Bayes-Optimality in Symmetric Zero-sum Games	Boosting Graph Structure Learning with Dummy Nodes	Fast Relative Entropy Coding with A* coding	Topology-aware Generalization of Decentralized SGD		Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation		Matching Learned Causal Effects of Neural Networks with Domain Priors
05:40 PM (Spotlights)		Combining Diverse Feature Priors	Content Addressable Memory Without Catastrophic Forgetting by Heteroassociation with a Fixed Scaffold		Sample and Communication-Efficient Decentralized Actor-Critic Algorithms with Finite-Time Analysis	Lazy Estimation of Variable Importance for Large Neural Networks	Accurate Quantization of Measures via Interacting Particle-based Optimization	Understanding Gradient Descent on the Edge of Stability in Deep Learning		Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack		Inferring Cause and Effect in the Presence of Heteroscedastic Noise
06:30 PM (Posters)									From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model Virtual #318 Steerable 3D Spherical Neurons Virtual #1103		Poster Session 1
07:00 PM (Socials)							Commonsense Knowledge Discovery and Acquisition

Time	Hall F	Room 327 - 329	Room 301 - 303	Room 309	Room 318 - 320	Room 310	Room 307	Room 308	Hall G	Virtual	Ballroom 1 & 2	Ballroom 3 & 4
Wed Jul 20, 2022
09:00 AM (Invited Talks)	Solving the Right Problems: Making ML Models Relevant to Healthcare and the Life Sciences
10:00 AM (Socials)										Un-Bookclub Haben: The Deafblind Woman Who Conquered Harvard Law
10:30 AM (Orals, Spotlights)	T: Learning Theory/Domain Adaptation Learning Domain Adaptive Object Detection with Probabilistic Teacher	OPT: First Order Adapting to Mixing Time in Stochastic Optimization with Markovian Data	PM: Variational Inference/Bayesian Models and Methods How Tempering Fixes Data Augmentation in Bayesian Neural Networks	DL: Theory On Numerical Integration in Neural Ordinary Differential Equations	Social Aspects/MISC Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings	T: Game Theory/RL/Planning A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision Processes	Reinforcement Learning: Deep RL Modeling Strong and Human-Like Gameplay with KL-Regularized Search		Applications Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification		Deep Learning Towards understanding how momentum improves generalization in deep learning	MISC: General Machine Learning Techniques Weisfeiler-Lehman Meets Gromov-Wasserstein
10:35 AM (Spotlights)	Adaptive Data Analysis with Correlated Observations			Reverse Engineering the Neural Tangent Kernel	Label-Free Explainability for Unsupervised Models		Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters		One-Pass Diversified Sampling with Application to Terabyte-Scale Genomic Sequence Streams		What Can Linear Interpolation of Neural Network Loss Landscapes Tell Us?	GenLabel: Mixup Relabeling using Generative Models
10:40 AM (Spotlights)	Efficient PAC Learning from the Crowd with Pairwise Comparisons			Principled Knowledge Extrapolation with GANs	Towards Theoretical Analysis of Transformation Complexity of ReLU DNNs		Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning		Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video Restoration		Deep equilibrium networks are sensitive to initialization statistics	When and How Mixup Improves Calibration
10:45 AM (Spotlights)	On the Statistical Benefits of Curriculum Learning			Informed Learning by Wide Neural Networks: Convergence, Generalization and Sampling Complexity	A Study of Face Obfuscation in ImageNet		Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models and Amortized Policy Search		ME-GAN: Learning Panoptic Electrocardio Representations for Multi-view ECG Synthesis Conditioned on Heart Diseases		Scaling-up Diverse Orthogonal Convolutional Networks by a Paraunitary Framework	On Transportation of Mini-batches: A Hierarchical Approach
10:50 AM (Spotlights)	Feature and Parameter Selection in Stochastic Linear Bandits	Fast Composite Optimization and Statistical Recovery in Federated Learning	Surrogate Likelihoods for Variational Annealed Importance Sampling	Data Augmentation as Feature Manipulation	Fair Representation Learning through Implicit Path Alignment	The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces	Generalized Data Distribution Iteration		Variational Mixtures of ODEs for Inferring Cellular Gene Expression Dynamics		Stability Based Generalization Bounds for Exponential Family Langevin Dynamics	VariGrow: Variational Architecture Growing for Task-Agnostic Continual Learning based on Bayesian Novelty
10:55 AM (Spotlights)	Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring	Beyond Worst-Case Analysis in Stochastic Approximation: Moment Estimation Improves Instance Complexity	Nonparametric Sparse Tensor Factorization with Hierarchical Gamma Processes	Convolutional and Residual Networks Provably Contain Lottery Tickets	Mitigating Neural Network Overconfidence with Logit Normalization	Extracting Latent State Representations with Linear Dynamics from Rich Observations	Optimizing Tensor Network Contraction Using Reinforcement Learning		Bayesian Imitation Learning for End-to-End Mobile Manipulation		Local Augmentation for Graph Neural Networks	Beyond Images: Label Noise Transition Matrix Estimation for Tasks with Lower-Quality Features
11:00 AM (Orals, Socials, Spotlights)	A new similarity measure for covariate shift with applications to nonparametric regression	Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning	Fat–Tailed Variational Inference with Anisotropic Tail Adaptive Flows	Feature Learning and Signal Propagation in Deep Neural Networks	Learning fair representation with a parametric integral probability metric	For Learning in Symmetric Teams, Local Optima are Global Nash Equilibria	History Compression via Language Models in Reinforcement Learning	Black in AI and Queer in AI Joint Social Event	De novo mass spectrometry peptide sequencing with a transformer model		On Non-local Convergence Analysis of Deep Linear Networks	A Model-Agnostic Randomized Learning Framework based on Random Hypothesis Subspace Sampling
11:05 AM (Orals, Spotlights)		Optimal Algorithms for Stochastic Multi-Level Compositional Optimization	Variational Sparse Coding with Learned Thresholding	Robust Training of Neural Networks Using Scale Invariant Architectures	Privacy for Free: How does Dataset Condensation Help Privacy?	Consensus Multiplicative Weights Update: Learning to Learn using Projector-based Game Signatures	REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer		Learning inverse folding from millions of predicted structures		Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum	Stable Conformal Prediction Sets
11:10 AM (Orals, Spotlights)		Finite-Sum Coupled Compositional Stochastic Optimization: Theory and Applications	Structured Stochastic Gradient MCMC			Learning Markov Games with Adversarial Opponents: Efficient Algorithms and Fundamental Limits
11:15 AM (Orals)		Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent	BAMDT: Bayesian Additive Semi-Multivariate Decision Trees for Nonparametric Regression
11:20 AM (Spotlights)	Contextual Bandits with Large Action Spaces: Made Practical
11:25 AM (Spotlights)	Identifiability Conditions for Domain Adaptation			Understanding Contrastive Learning Requires Incorporating Inductive Biases	Fair Generalized Linear Models with a Convex Penalty		LeNSE: Learning To Navigate Subgraph Embeddings for Large-Scale Combinatorial Optimisation		Guided-TTS: A Diffusion Model for Text-to-Speech via Classifier Guidance		Diversified Adversarial Attacks based on Conjugate Gradient Method	Rethinking Fano’s Inequality in Ensemble Learning
11:30 AM (Spotlights)	Streaming Algorithms for High-Dimensional Robust Statistics			Implicit Regularization with Polynomial Growth in Deep Tensor Factorization	HyperPrompt: Prompt-based Task-Conditioning of Transformers	Strategic Instrumental Variable Regression: Recovering Causal Relationships From Strategic Responses	Efficient Learning for AlphaZero via Path Consistency		MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection		On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features	FITNESS: (Fine Tune on New and Similar Samples) to detect anomalies in streams with drift and outliers
11:35 AM (Spotlights)	Popular decision tree algorithms are provably noise tolerant	Statistical inference with implicit SGD: proximal Robbins-Monro vs. Polyak-Ruppert	Variational Inference with Locally Enhanced Bounds for Hierarchical Models	Deep Network Approximation in Terms of Intrinsic Parameters	Validating Causal Inference Methods	Learning to Infer Structures of Network Games	A data-driven approach for learning to control computers		Proximal Exploration for Model-guided Protein Sequence Design		On the Equivalence Between Temporal and Static Equivariant Graph Representations	Improving Mini-batch Optimal Transport via Partial Transportation
11:40 AM (Spotlights)	Understanding and Improving Knowledge Graph Embedding for Entity Alignment	ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!	Centroid Approximation for Bootstrap: Improving Particle Quality at Inference	Coin Flipping Neural Networks	The Multivariate Community Hawkes Model for Dependent Relational Events in Continuous-time Networks	Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation	Zero-Shot Reward Specification via Grounded Natural Language		Tranception: Protein Fitness Prediction with Autoregressive Transformers and Inference-time Retrieval		Robust Training under Label Noise by Over-parameterization	Near-optimal rate of consistency for linear models with missing values
11:45 AM (Spotlights)	Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning	Communication-Efficient Adaptive Federated Learning	Deep Reference Priors: What is the best way to pretrain a model?	Benefits of Overparameterized Convolutional Residual Networks: Function Approximation under Smoothness Constraint	Scalable Deep Gaussian Markov Random Fields for General Graphs	Near-Optimal Learning of Extensive-Form Games with Imperfect Information	How to Stay Curious while avoiding Noisy TVs using Aleatoric Uncertainty Estimation		How to Fill the Optimum Set? Population Gradient Descent with Harmless Diversity		Implicit Bias of the Step Size in Linear Diagonal Neural Networks	Permutation Search of Tensor Network Structures via Local Sampling
11:50 AM (Spotlights)	Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees	RECAPP: Crafting a More Efficient Catalyst for Convex Optimization		More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize	Anytime Information Cascade Popularity Prediction via Self-Exciting Processes	Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation	Model-Value Inconsistency as a Signal for Epistemic Uncertainty		Examining Scaling and Transfer of Language Model Architectures for Machine Translation		Extended Unconstrained Features Model for Exploring Deep Neural Collapse	Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?
11:55 AM (Spotlights)	Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyond	Kill a Bird with Two Stones: Closing the Convergence Gaps in Non-Strongly Convex Optimization by Directly Accelerated SVRG with Double Compensation and Snapshots		SE(3) Equivariant Graph Neural Networks with Complete Local Frames	Deep Variational Graph Convolutional Recurrent Network for Multivariate Time Series Anomaly Detection		Improving Policy Optimization with Generalist-Specialist Learning		State Transition of Dendritic Spines Improves Learning of Sparse Spiking Neural Networks		Score-Guided Intermediate Level Optimization: Fast Langevin Mixing for Inverse Problems	DNNR: Differential Nearest Neighbors Regression
01:15 PM (Orals, Spotlights)	APP: Chemistry and Drug Discovery MemSR: Training Memory-efficient Lightweight Model for Image Super-Resolution	T: Online Learning and Bandits/Learning Theory Generative Trees: Adversarial and Copycat	PM: Bayesian Models and Methods Bayesian Continuous-Time Tucker Decomposition	SA: Trustworthy Machine Learning Tight and Robust Private Mean Estimation with Few Users	DL: Robustness Generating Distributional Adversarial Examples to Evade Statistical Detectors	DL: Robustness DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning	Reinforcement Learning Biased Gradient Estimate with Drastic Variance Reduction for Meta Reinforcement Learning		MISC: Representation Learning/Causality Decomposing Temporal High-Order Interactions via Latent ODEs		Deep Learning/APP:Computer Vision From data to functa: Your data point is a function and you can treat it like one	Theory Choosing Answers in Epsilon-Best-Answer Identification for Linear Bandits
01:20 PM (Spotlights)	PINs: Progressive Implicit Networks for Multi-Scale Neural Representations				Improving Out-of-Distribution Robustness via Selective Augmentation	Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion	Analysis of Stochastic Processes through Replay Buffers		Log-Euclidean Signatures for Intrinsic Distances Between Unaligned Datasets		DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training	On the Finite-Time Performance of the Knowledge Gradient Algorithm
01:25 PM (Spotlights)	Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders				Modeling Adversarial Noise for Adversarial Training	RetrievalGuard: Provably Robust 1-Nearest Neighbor Image Retrieval	Cascaded Gaps: Towards Logarithmic Regret for Risk-Sensitive Reinforcement Learning		DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneck		Differentiable Top-k Classification Learning	Expression might be enough: representing pressure and demand for reinforcement learning based traffic signal control
01:30 PM (Spotlights)	Generative Coarse-Graining of Molecular Conformations				Improving Adversarial Robustness via Mutual Information Estimation	Modeling Structure with Undirected Neural Networks	Communicating via Markov Decision Processes		End-to-End Balancing for Causal Continuous Treatment-Effect Estimation		Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks	Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers
01:35 PM (Spotlights)	LIMO: Latent Inceptionism for Targeted Molecule Generation	A Resilient Distributed Boosting Algorithm	Approximate Bayesian Computation with Domain Expert in the Loop	QSFL: A Two-Level Uplink Communication Optimization Framework for Federated Learning	FOCUS: Familiar Objects in Common and Uncommon Settings	Certified Neural Network Watermarks with Randomized Smoothing	PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation		Role-based Multiplex Network Embedding		Characterizing and Overcoming the Greedy Nature of Learning in Multi-modal Deep Neural Networks	No-Regret Learning in Time-Varying Zero-Sum Games
01:40 PM (Spotlights)	Learning to Separate Voices by Spatial Regions	Online Learning and Pricing with Reusable Resources: Linear Bandits with Sub-Exponential Rewards	Discrete Probabilistic Inverse Optimal Transport	Robustness and Accuracy Could Be Reconcilable by (Proper) Definition	Query-Efficient and Scalable Black-Box Adversarial Attacks on Discrete Sequential Data via Bayesian Optimization	Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation	DNS: Determinantal Point Process Based Neural Network Sampler for Ensemble Reinforcement Learning		Measure Estimation in the Barycentric Coding Model		Training Your Sparse Neural Network Better with Any Mask	Achieving Minimax Rates in Pool-Based Batch Active Learning
01:45 PM (Orals, Spotlights)	3DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker Design	On Well-posedness and Minimax Optimal Rates of Nonparametric Q-function Estimation in Off-policy Evaluation	Easy Variational Inference for Categorical Models via an Independent Binary Approximation	Sanity Simulations for Saliency Methods	Test-Time Training Can Close the Natural Distribution Shift Performance Gap in Deep Learning Based Compressed Sensing	Adversarial Vulnerability of Randomized Ensembles	Planning with Diffusion for Flexible Behavior Synthesis		RieszNet and ForestRiesz: Automatic Debiased Machine Learning with Neural Nets and Random Forests		Federated Learning with Positive and Unlabeled Data	Active Multi-Task Representation Learning
01:50 PM (Orals, Spotlights)		Congested Bandits: Optimal Routing via Short-term Resets	Streaming Inference for Infinite Feature Models	Out-of-Distribution Detection with Deep Nearest Neighbors	A Dynamical System Perspective for Lipschitz Neural Networks	Robustness Verification for Contrastive Learning					Generating 3D Molecules for Target Protein Binding	Active fairness auditing
01:55 PM (Spotlights)		Stochastic Rising Bandits	Optimizing Sequential Experimental Design with Deep Reinforcement Learning	Differentially Private Maximal Information Coefficients
02:00 PM (Orals)		Agnostic Learnability of Halfspaces via Logistic Loss	Function-space Inference with Sparse Implicit Processes	Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data
02:05 PM (Spotlights)	3D Infomax improves GNNs for Molecular Property Prediction						A Temporal-Difference Approach to Policy Gradient Estimation		Counterfactual Transportability: A Formal Approach
02:10 PM (Spotlights)	Biological Sequence Design with GFlowNets				Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)	The CLRS Algorithmic Reasoning Benchmark	MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay Buffer		Identification of Linear Non-Gaussian Latent Hierarchical Structure		Sparse Double Descent: Where Network Pruning Aggravates Overfitting	Metric-Fair Active Learning
02:15 PM (Spotlights)	Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets				Neurotoxin: Durable Backdoors in Federated Learning	Finding Global Homophily in Graph Neural Networks When Meeting Heterophily	Reinforcement Learning from Partial Observation: Linear Function Approximation with Provable Sample Efficiency		COAT: Measuring Object Compositionality in Emergent Representations		Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPs	Metric-Fair Classifier Derandomization
02:20 PM (Spotlights)	Retroformer: Pushing the Limits of End-to-end Retrosynthesis Transformer	Fluctuations, Bias, Variance & Ensemble of Learners: Exact Asymptotics for Convex Losses in High-Dimension	Variational Inference for Infinitely Deep Neural Networks	On the Difficulty of Defending Self-Supervised Learning against Model Extraction	Bayesian Learning with Information Gain Provably Bounds Risk for a Robust Adversarial Defense	Understanding Robust Generalization in Learning Regular Languages	Actor-Critic based Improper Reinforcement Learning		Generalization and Robustness Implications in Object-Centric Learning		Revisiting Consistency Regularization for Deep Partial Label Learning	Interactively Learning Preference Constraints in Linear Bandits
02:25 PM (Spotlights)	Constrained Optimization with Dynamic Bound-scaling for Effective NLP Backdoor Defense	PDE-Based Optimal Strategy for Unconstrained Online Learning	Personalized Federated Learning via Variational Bayesian Inference	Adversarial Attack and Defense for Non-Parametric Two-Sample Tests	Maximum Likelihood Training for Score-based Diffusion ODEs by High Order Denoising Score Matching	Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification	On the Sample Complexity of Learning Infinite-horizon Discounted Linear Kernel MDPs		NAFS: A Simple yet Tough-to-beat Baseline for Graph Representation Learning		Stochastic smoothing of the top-K calibrated hinge loss for deep imbalanced classification	Convergence of Uncertainty Sampling for Active Learning
02:30 PM (Spotlights)	Path-Aware and Structure-Preserving Generation of Synthetically Accessible Molecules	Provable Acceleration of Heavy Ball beyond Quadratics for a Class of Polyak-Lojasiewicz Functions when the Non-Convexity is Averaged-Out	Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling	Certified Adversarial Robustness Under the Bounded Support Set	Fast Lossless Neural Compression with Integer-Only Discrete Flows	AdAUC: End-to-end Adversarial AUC Optimization Against Long-tail Problems	The Geometry of Robust Value Functions		Action-Sufficient State Representation Learning for Control with Structural Constraints		A Unified Weight Initialization Paradigm for Tensorial Convolutional Neural Networks	Thompson Sampling for Robust Transfer in Multi-Task Bandits
02:35 PM (Spotlights)	EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction	On Learning Mixture of Linear Regressions in the Non-Realizable Setting	Bayesian Deep Embedding Topic Meta-Learner	Predicting Out-of-Distribution Error with the Projection Norm	SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization	A Modern Self-Referential Weight Matrix That Learns to Modify Itself	Denoised MDPs: Learning World Models Better Than the World Itself				PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Information	Constants Matter: The Performance Gains of Active Learning
02:40 PM (Spotlights)		Random Forest Density Estimation	Efficient Approximate Inference for Stationary Kernel on Frequency Domain	Adversarially Robust Models may not Transfer Better: Sufficient Conditions for Domain Transferability from the View of Regularization	SCHA-VAE: Hierarchical Context Aggregation for Few-Shot Generation	Short-Term Plasticity Neurons Learning to Learn and Forget					Multicoated Supermasks Enhance Hidden Networks	Cross-Space Active Learning on Graph Convolutional Networks
03:15 PM (Invited Talks)	Synthetic Control Methods and Difference-In-Differences
04:00 PM (Socials)										Women in Artificial Intelligence and Machine Learning for Mental Health Applications
04:30 PM (Spotlights)	Applications

Sun Jul 17, 2022

Mon Jul 18, 2022

Tue Jul 19, 2022

Wed Jul 20, 2022