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
The State of Sparse Training in Deep Reinforcement Learning
The Teaching Dimension of Regularized Kernel Learners
The Unsurprising Effectiveness of Pre-Trained Vision Models for Control
Thompson Sampling for (Combinatorial) Pure Exploration
Thompson Sampling for Robust Transfer in Multi-Task Bandits
Three-stage Evolution and Fast Equilibrium for SGD with Non-degerate Critical Points
Thresholded Lasso Bandit
Tight and Robust Private Mean Estimation with Few Users
Time Is MattEr: Temporal Self-supervision for Video Transformers
Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning
To Smooth or Not? When Label Smoothing Meets Noisy Labels
Toward Compositional Generalization in Object-Oriented World Modeling
Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods
Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent
Towards Scaling Difference Target Propagation by Learning Backprop Targets
Towards Theoretical Analysis of Transformation Complexity of ReLU DNNs
Towards Understanding Sharpness-Aware Minimization
Towards Uniformly Superhuman Autonomy via Subdominance Minimization
TPC: Transformation-Specific Smoothing for Point Cloud Models
Tractable Dendritic RNNs for Reconstructing Nonlinear Dynamical Systems
Tractable Uncertainty for Structure Learning
Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect Four
Training Discrete Deep Generative Models via Gapped Straight-Through Estimator
Training OOD Detectors in their Natural Habitats
Training Your Sparse Neural Network Better with Any Mask
Tranception: Protein Fitness Prediction with Autoregressive Transformers and Inference-time Retrieval
Transfer and Marginalize: Explaining Away Label Noise with Privileged Information
Transfer Learning In Differential Privacy's Hybrid-Model
Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling
Transformers are Meta-Reinforcement Learners
Translatotron 2: High-quality direct speech-to-speech translation with voice preservation
TSPipe: Learn from Teacher Faster with Pipelines
TURF: Two-Factor, Universal, Robust, Fast Distribution Learning Algorithm
UAST: Uncertainty-Aware Siamese Tracking
Unaligned Supervision for Automatic Music Transcription in The Wild
Uncertainty Modeling in Generative Compressed Sensing
UnderGrad: A Universal Black-Box Optimization Method with Almost Dimension-Free Convergence Rate Guarantees
Understanding and Improving Knowledge Graph Embedding for Entity Alignment
Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy
Understanding Contrastive Learning Requires Incorporating Inductive Biases
Understanding Dataset Difficulty with $\mathcal{V}$-Usable Information
Understanding Dataset Difficulty with-Usable Information
Understanding Dataset Difficulty with V-Usable Information.
Understanding Doubly Stochastic Clustering
Understanding Gradient Descent on the Edge of Stability in Deep Learning
Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyond
Understanding Instance-Level Impact of Fairness Constraints
Understanding Policy Gradient Algorithms: A Sensitivity-Based Approach
Understanding Robust Generalization in Learning Regular Languages
Understanding Robust Overfitting of Adversarial Training and Beyond

« prev Page 22/24 next »