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
Minimizing Control for Credit Assignment with Strong Feedback
Minimum Cost Intervention Design for Causal Effect Identification
Mirror Learning: A Unifying Framework of Policy Optimisation
Mitigating Gender Bias in Face Recognition using the von Mises-Fisher Mixture Model
Mitigating Modality Collapse in Multimodal VAEs via Impartial Optimization
Mitigating Neural Network Overconfidence with Logit Normalization
Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)
Model Agnostic Sample Reweighting for Out-of-Distribution Learning
Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models and Amortized Policy Search
Model-Free Opponent Shaping
Modeling Adversarial Noise for Adversarial Training
Modeling Irregular Time Series with Continuous Recurrent Units
Modeling Strong and Human-Like Gameplay with KL-Regularized Search
Modeling Structure with Undirected Neural Networks
Model Selection in Batch Policy Optimization
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
ModLaNets: Learning Generalisable Dynamics via Modularity and Physical Inductive Bias
Modular Conformal Calibration
Molecular Representation Learning via Heterogeneous Motif Graph Neural Networks
Monarch: Expressive Structured Matrices for Efficient and Accurate Training
More Efficient Sampling for Tensor Decomposition With Worst-Case Guarantees
More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize
Multi-attention YOLOv5 for Recognition of Abnormal Helmets Wearing in Power Stations
Multiclass learning with margin: exponential rates with no bias-variance trade-off
Multicoated Supermasks Enhance Hidden Networks
Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts
Multi-Level Branched Regularization for Federated Learning
Multiple-Play Stochastic Bandits with Shareable Finite-Capacity Arms
Multirate Training of Neural Networks
Multi Resolution Analysis (MRA) for Approximate Self-Attention
Multi-scale Feature Learning Dynamics: Insights for Double Descent
Multi-slots Online Matching with High Entropy
Multi-Task Learning as a Bargaining Game
Near-Exact Recovery for Tomographic Inverse Problems via Deep Learning
Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation
Nearly Optimal Catoni's M-estimator for Infinite Variance
Nearly Optimal Policy Optimization with Stable at Any Time Guarantee
Near-optimal rate of consistency for linear models with missing values
Nested Bandits
Nesterov Accelerated Shuffling Gradient Method for Convex Optimization
NeuralEF: Deconstructing Kernels by Deep Neural Networks
Neural Fisher Discriminant Analysis: Optimal Neural Network Embeddings in Polynomial Time
Neural Implicit Dictionary Learning via Mixture-of-Expert Training
Neural Inverse Kinematic
Neural Inverse Transform Sampler
Neural Language Models are not Born Equal to Fit Brain Data, but Training Helps
Neural Laplace: Learning diverse classes of differential equations in the Laplace domain
Neural Network Poisson Models for Behavioural and Neural Spike Train Data
Neural Network Pruning Denoises the Features and Makes Local Connectivity Emerge in Visual Tasks
Neural Network Weights Do Not Converge to Stationary Points: An Invariant Measure Perspective

« prev Page 14/24 next »