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
Iterative Double Sketching for Faster Least-Squares Optimization
Iterative Hard Thresholding with Adaptive Regularization: Sparser Solutions Without Sacrificing Runtime
It's Raw! Audio Generation with State-Space Models
Kernelized Multiplicative Weights for 0/1-Polyhedral Games: Bridging the Gap Between Learning in Extensive-Form and Normal-Form Games
Kernel Methods for Radial Transformed Compositional Data with Many Zeros
Kill a Bird with Two Stones: Closing the Convergence Gaps in Non-Strongly Convex Optimization by Directly Accelerated SVRG with Double Compensation and Snapshots
Knowledge Base Question Answering by Case-based Reasoning over Subgraphs
Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations
Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics
Label-Descriptive Patterns and Their Application to Characterizing Classification Errors
Label-Free Explainability for Unsupervised Models
Label Ranking through Nonparametric Regression
Lagrangian Method for Q-Function Learning (with Applications to Machine Translation)
Langevin Monte Carlo for Contextual Bandits
Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents
Large Batch Experience Replay
Large-Scale Graph Neural Architecture Search
Large-scale Stochastic Optimization of NDCG Surrogates for Deep Learning with Provable Convergence
Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression
Latent Diffusion Energy-Based Model for Interpretable Text Modelling
Latent Outlier Exposure for Anomaly Detection with Contaminated Data
Lazy Estimation of Variable Importance for Large Neural Networks
LCANets: Lateral Competition Improves Robustness Against Corruption and Attack
Learning Augmented Binary Search Trees
Learning-based Optimisation of Particle Accelerators Under Partial Observability Without Real-World Training
Learning Bellman Complete Representations for Offline Policy Evaluation
Learning Domain Adaptive Object Detection with Probabilistic Teacher
Learning Dynamics and Generalization in Deep Reinforcement Learning
Learning Efficient and Robust Ordinary Differential Equations via Invertible Neural Networks
Learning fair representation with a parametric integral probability metric
Learning from a Learning User for Optimal Recommendations
Learning from Counterfactual Links for Link Prediction
Learning from Demonstration: Provably Efficient Adversarial Policy Imitation with Linear Function Approximation
Learning General Halfspaces with Adversarial Label Noise via Online Gradient Descent
Learning Infinite-horizon Average-reward Markov Decision Process with Constraints
Learning inverse folding from millions of predicted structures
Learning Iterative Reasoning through Energy Minimization
Learning Markov Games with Adversarial Opponents: Efficient Algorithms and Fundamental Limits
Learning Mixtures of Linear Dynamical Systems
Learning Multiscale Transformer Models for Sequence Generation
Learning of Cluster-based Feature Importance for Electronic Health Record Time-series
Learning Stochastic Shortest Path with Linear Function Approximation
Learning Symmetric Embeddings for Equivariant World Models
Learning the Solution Operator of Boundary Value Problems using Graph Neural Networks
Learning to Cut by Looking Ahead: Cutting Plane Selection via Imitation Learning
Learning to Estimate and Refine Fluid Motion with Physical Dynamics
Learning to Hash Robustly, Guaranteed
Learning to Incorporate Texture Saliency Adaptive Attention to Image Cartoonization
Learning to Infer Structures of Network Games
Learning to Predict Graphs with Fused Gromov-Wasserstein Barycenters

« prev Page 12/24 next »