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
IDYNO: Learning Nonparametric DAGs from Interventional Dynamic Data
IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages
Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging
Imitation Learning by Estimating Expertise of Demonstrators
Implicit Bias of Linear Equivariant Networks
Implicit Bias of the Step Size in Linear Diagonal Neural Networks
Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks
Implicit Regularization with Polynomial Growth in Deep Tensor Factorization
Importance Weighted Kernel Bayes' Rule
Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation
Improved Convergence Rates for Sparse Approximation Methods in Kernel-Based Learning
Improved Ice Cream Detection Algorithm Based on YOLOv5
Improved No-Regret Algorithms for Stochastic Shortest Path with Linear MDP
Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data
Improved Regret for Differentially Private Exploration in Linear MDP
Improved StyleGAN-v2 based Inversion for Out-of-Distribution Images
Improve Single-Point Zeroth-Order Optimization Using High-Pass and Low-Pass Filters
Improving Adversarial Robustness via Mutual Information Estimation
Improving Ensemble Distillation With Weight Averaging and Diversifying Perturbation
Improving Language Models by Retrieving from Trillions of Tokens
Improving Mini-batch Optimal Transport via Partial Transportation
Improving Policy Optimization with Generalist-Specialist Learning
Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification
Improving Screening Processes via Calibrated Subset Selection
Improving Task-free Continual Learning by Distributionally Robust Memory Evolution
Improving Transformers with Probabilistic Attention Keys
Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence
Individual Preference Stability for Clustering
Individual Reward Assisted Multi-Agent Reinforcement Learning
Inducing Causal Structure for Interpretable Neural Networks
Inductive Matrix Completion: No Bad Local Minima and a Fast Algorithm
Inferring Cause and Effect in the Presence of Heteroscedastic Noise
Influence-Augmented Local Simulators: a Scalable Solution for Fast Deep RL in Large Networked Systems
Information Discrepancy in Strategic Learning
Informed Learning by Wide Neural Networks: Convergence, Generalization and Sampling Complexity
Injecting Logical Constraints into Neural Networks via Straight-Through Estimators
Input-agnostic Certified Group Fairness via Gaussian Parameter Smoothing
Instance Dependent Regret Analysis of Kernelized Bandits
Instrumental Variable Regression with Confounder Balancing
Interactive Correlation Clustering with Existential Cluster Constraints
Interactive Inverse Reinforcement Learning for Cooperative Games
Interactively Learning Preference Constraints in Linear Bandits
International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA
Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism
Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings
Interpretable Off-Policy Learning via Hyperbox Search
Interventional Contrastive Learning with Meta Semantic Regularizer
Invariant Ancestry Search
Inverse Contextual Bandits: Learning How Behavior Evolves over Time
Investigating Generalization by Controlling Normalized Margin

« prev Page 11/24 next »