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
Understanding The Robustness in Vision Transformers
Understanding the unstable convergence of gradient descent
Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces
Unified Scaling Laws for Routed Language Models
UniRank: Unimodal Bandit Algorithms for Online Ranking
Universal and data-adaptive algorithms for model selection in linear contextual bandits
Universal Hopfield Networks: A General Framework for Single-Shot Associative Memory Models
Universality of Winning Tickets: A Renormalization Group Perspective
Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers
Unsupervised Detection of Contextualized Embedding Bias with Application to Ideology
Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video Restoration
Unsupervised Ground Metric Learning Using Wasserstein Singular Vectors
Unsupervised Image Representation Learning with Deep Latent Particles
Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion
Utility Theory for Sequential Decision Making
Utilizing Expert Features for Contrastive Learning of Time-Series Representations
Validating Causal Inference Methods
Value Function based Difference-of-Convex Algorithm for Bilevel Hyperparameter Selection Problems
Variational Feature Pyramid Networks
Variational Inference for Infinitely Deep Neural Networks
Variational Inference with Locally Enhanced Bounds for Hierarchical Models
Variational Mixtures of ODEs for Inferring Cellular Gene Expression Dynamics
Variational nearest neighbor Gaussian process
Variational On-the-Fly Personalization
Variational Sparse Coding with Learned Thresholding
Variational Wasserstein gradient flow
VariGrow: Variational Architecture Growing for Task-Agnostic Continual Learning based on Bayesian Novelty
VarScene: A Deep Generative Model for Realistic Scene Graph Synthesis
Versatile Dueling Bandits: Best-of-both World Analyses for Learning from Relative Preferences
Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching
Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learning
Visual Attention Emerges from Recurrent Sparse Reconstruction
ViT-NeT: Interpretable Vision Transformers with Neural Tree Decoder
VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix
VLUE: A Multi-Task Multi-Dimension Benchmark for Evaluating Vision-Language Pre-training
Volatility Based Kernels and Moving Average Means for Accurate Forecasting with Gaussian Processes
Weather Classification for Multi-class Weather Image Based on CNN
Weisfeiler-Lehman Meets Gromov-Wasserstein
Welfare Maximization in Competitive Equilibrium: Reinforcement Learning for Markov Exchange Economy
What Can Linear Interpolation of Neural Network Loss Landscapes Tell Us?
What Dense Graph Do You Need for Self-Attention?
What Language Model Architecture and Pretraining Objective Works Best for Zero-Shot Generalization?
When and How Mixup Improves Calibration
When Are Linear Stochastic Bandits Attackable?
When AUC meets DRO: Optimizing Partial AUC for Deep Learning with Non-Convex Convergence Guarantee
Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error
Why the Rich Get Richer? On the Balancedness of Random Partition Models
Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling
Wide Neural Networks Forget Less Catastrophically
Winning the Lottery Ahead of Time: Efficient Early Network Pruning

« prev Page 23/24 next »