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
Parametric Visual Program Induction with Function Modularization
Parsimonious Learning-Augmented Caching
Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition
Partial Counterfactual Identification from Observational and Experimental Data
Partial disentanglement for domain adaptation
Partial Label Learning via Label Influence Function
Particle Transformer for Jet Tagging
Path-Aware and Structure-Preserving Generation of Synthetically Accessible Molecules
pathGCN: Learning General Graph Spatial Operators from Paths
Path-Gradient Estimators for Continuous Normalizing Flows
PDO-s3DCNNs: Partial Differential Operator Based Steerable 3D CNNs
Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning
Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning
Permutation Search of Tensor Network Structures via Local Sampling
Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning
Personalized Federated Learning through Local Memorization
Personalized Federated Learning via Variational Bayesian Inference
Pessimism meets VCG: Learning Dynamic Mechanism Design via Offline Reinforcement Learning
Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets
Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity
Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning
PINs: Progressive Implicit Networks for Multi-Scale Neural Representations
Planning with Diffusion for Flexible Behavior Synthesis
Plan Your Target and Learn Your Skills: Transferable State-Only Imitation Learning via Decoupled Policy Optimization
PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Information
PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance
Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations
Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks
Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets
POEM: Out-of-Distribution Detection with Posterior Sampling
POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging
PoF: Post-Training of Feature Extractor for Improving Generalization
Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RL
Policy Gradient Method For Robust Reinforcement Learning
Popular decision tree algorithms are provably noise tolerant
Position Prediction as an Effective Pretraining Strategy
Power-Law Escape Rate of SGD
Practical Almost-Linear-Time Approximation Algorithms for Hybrid and Overlapping Graph Clustering
Preconditioning for Scalable Gaussian Process Hyperparameter Optimization
Predicting Out-of-Distribution Error with the Projection Norm
Principal Component Flows
Principled Knowledge Extrapolation with GANs
Prioritized Training on Points that are Learnable, Worth Learning, and not yet Learnt
Privacy for Free: How does Dataset Condensation Help Privacy?
Private Adaptive Optimization with Side information
Private frequency estimation via projective geometry
Private optimization in the interpolation regime: faster rates and hardness results
Private Streaming SCO in $\ell_p$ geometry with Applications in High Dimensional Online Decision Making
Private Streaming SCO in ℓp geometry with Applications in High Dimensional Online Decision Making
Probabilistically Robust Learning: Balancing Average and Worst-case Performance

« prev Page 17/24 next »