ICML 2022

1,154 papers

Top Research Directions

Research directions most represented by ICML 2022 papers.

The Non-Linear Function Approximation Gap in Reinforcement Learning 23
Clean Accuracy Degradation in Machine Learning Defenses 22
Scaling Gaussian Processes Beyond Cubic Complexity 17
Provably Efficient Reinforcement Learning with Linear MDPs 15
The Function Approximation Gap in Reinforcement Learning Theory 15
Bypassing the Computational Bottleneck of Adversarial Training 14
Loss Landscape Flatness and the Generalization Gap 13
Mitigating Gradient Variance in Policy Optimization 13
Distribution Shift in Offline Reinforcement Learning 12
Scaling Bandit Learning to Large Action Spaces 10
Multi-Agent Learning Under Bandit Feedback 10
Horizon Free Bounds in Reinforcement Learning 10
Periodic Synchronization for Communication Efficient Distributed Learning 10
Optimistic Exploration for Efficient Reinforcement Learning 10
Matrix-Free Curvature Estimation for Deep Learning 10

Top Authors

AuthorPapers
Zhangyang Wang9
Zhaoran Wang9
Zhuoran Yang9
Bo Li7
Jun Zhu7
Shandian Zhe7
Tianbao Yang7
Bernhard Schölkopf6
Bo Han6
Manzil Zaheer6
Mihaela van der Schaar6
Nhat Ho6
Pranjal Awasthi6
Sergey Levine6
Tianlong Chen6
Yang Liu6
Andreas Krause5
David Woodruff5
Michael W. Mahoney5
Peter Richtárik5

Impactful Papers

Papers from ICML 2022 that shaped research clusters.

Foundational

Influential

Papers

Title
Compressed-VFL: Communication-Efficient Learning with Vertically Partitioned Data
Confidence Score for Source-Free Unsupervised Domain Adaptation
Conformal Prediction Sets with Limited False Positives
Congested Bandits: Optimal Routing via Short-term Resets
Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation
Consensus Multiplicative Weights Update: Learning to Learn using Projector-based Game Signatures
Consistent Polyhedral Surrogates for Top-k Classification and Variants
Constants Matter: The Performance Gains of Active Learning
Constrained Gradient Descent: A Powerful and Principled Evasion Attack Against Neural Networks
Constrained Offline Policy Optimization
Constrained Optimization with Dynamic Bound-scaling for Effective NLP Backdoor Defense
Constrained Variational Policy Optimization for Safe Reinforcement Learning
Constraint-based graph network simulator
Content Addressable Memory Without Catastrophic Forgetting by Heteroassociation with a Fixed Scaffold
ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers
Context-Aware Drift Detection
Contextual Bandits with Large Action Spaces: Made Practical
Contextual Bandits with Smooth Regret: Efficient Learning in Continuous Action Spaces
Contextual Information-Directed Sampling
Continual Learning via Sequential Function-Space Variational Inference
Continual Learning with Guarantees via Weight Interval Constraints
Continual Repeated Annealed Flow Transport Monte Carlo
Continuous-Time Analysis of Accelerated Gradient Methods via Conservation Laws in Dilated Coordinate Systems
Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations
Contrastive Mixture of Posteriors for Counterfactual Inference, Data Integration and Fairness
Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning
Controlling Conditional Language Models without Catastrophic Forgetting
Convergence and Recovery Guarantees of the K-Subspaces Method for Subspace Clustering
Convergence of Invariant Graph Networks
Convergence of Policy Gradient for Entropy Regularized MDPs with Neural Network Approximation in the Mean-Field Regime
Convergence of Uncertainty Sampling for Active Learning
Convergence Rates of Non-Convex Stochastic Gradient Descent Under a Generic Lojasiewicz Condition and Local Smoothness
Convolutional and Residual Networks Provably Contain Lottery Tickets
Cooperative Online Learning in Stochastic and Adversarial MDPs
Coordinated Attacks against Contextual Bandits: Fundamental Limits and Defense Mechanisms
Coordinated Double Machine Learning
Correlated Quantization for Distributed Mean Estimation and Optimization
Correlation Clustering via Strong Triadic Closure Labeling: Fast Approximation Algorithms and Practical Lower Bounds
Co-training Improves Prompt-based Learning for Large Language Models
Counterfactual Prediction for Outcome-Oriented Treatments
Counterfactual Transportability: A Formal Approach
Cross-Space Active Learning on Graph Convolutional Networks
CtrlFormer: Learning Transferable State Representation for Visual Control via Transformer
Curriculum Reinforcement Learning via Constrained Optimal Transport
Cycle Representation Learning for Inductive Relation Prediction
Data Augmentation as Feature Manipulation
Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)
Data-Efficient Double-Win Lottery Tickets from Robust Pre-training
Datamodels: Understanding Predictions with Data and Data with Predictions
Dataset Condensation via Efficient Synthetic-Data Parameterization

« prev Page 5/24 next »