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
Probabilistic Bilevel Coreset Selection
Probabilistic ODE Solutions in Millions of Dimensions
ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning
ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training
Prompting Decision Transformer for Few-Shot Policy Generalization
Prototype-Anchored Learning for Learning with Imperfect Annotations
Provable Acceleration of Heavy Ball beyond Quadratics for a Class of Polyak-Lojasiewicz Functions when the Non-Convexity is Averaged-Out
Provable Domain Generalization via Invariant-Feature Subspace Recovery
Provable Reinforcement Learning with a Short-Term Memory
Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Performance
Provably Adversarially Robust Nearest Prototype Classifiers
Provably Efficient Offline Reinforcement Learning for Partially Observable Markov Decision Processes
Proving Theorems using Incremental Learning and Hindsight Experience Replay
Proximal and Federated Random Reshuffling
Proximal Denoiser for Convergent Plug-and-Play Optimization with Nonconvex Regularization
Proximal Exploration for Model-guided Protein Sequence Design
ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!
Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images
QSFL: A Two-Level Uplink Communication Optimization Framework for Federated Learning
Quant-BnB: A Scalable Branch-and-Bound Method for Optimal Decision Trees with Continuous Features
Quantification and Analysis of Layer-wise and Pixel-wise Information Discarding
Quantifying and Learning Linear Symmetry-Based Disentanglement
Quantum-Inspired Algorithms from Randomized Numerical Linear Algebra
Random Forest Density Estimation
Random Gegenbauer Features for Scalable Kernel Methods
RankSim: Ranking Similarity Regularization for Deep Imbalanced Regression
Reachability Constrained Reinforcement Learning
RECAPP: Crafting a More Efficient Catalyst for Convex Optimization
Reconstructing Nonlinear Dynamical Systems from Multi-Modal Time Series
Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs
Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks
Re-evaluating Word Mover's Distance
Refined Convergence Rates for Maximum Likelihood Estimation under Finite Mixture Models
Region-Based Semantic Factorization in GANs
Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation
Regret Minimization with Performative Feedback
Reinforcement Learning from Partial Observation: Linear Function Approximation with Provable Sample Efficiency
Reinforcement Learning with Action-Free Pre-Training from Videos
Removing Batch Normalization Boosts Adversarial Training
Representation Topology Divergence: A Method for Comparing Neural Network Representations
Residual-Based Sampling for Online Outlier-Robust PCA
Resilient and Communication Efficient Learning for Heterogeneous Federated Systems
Rethinking Attention-Model Explainability through Faithfulness Violation Test
Rethinking Fano's Inequality in Ensemble Learning
Rethinking Graph Neural Networks for Anomaly Detection
Rethinking Image-Scaling Attacks: The Interplay Between Vulnerabilities in Machine Learning Systems
RetrievalGuard: Provably Robust 1-Nearest Neighbor Image Retrieval
Retroformer: Pushing the Limits of End-to-end Retrosynthesis Transformer
Reverse Engineering $\ell_p$ attacks: A block-sparse optimization approach with recovery guarantees
Reverse Engineering ℓp attacks: A block-sparse optimization approach with recovery guarantees

« prev Page 18/24 next »