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
Stabilizing Off-Policy Deep Reinforcement Learning from Pixels
Stabilizing Q-learning with Linear Architectures for Provable Efficient Learning
Stable Conformal Prediction Sets
Staged Training for Transformer Language Models
State Transition of Dendritic Spines Improves Learning of Sparse Spiking Neural Networks
Statistical inference with implicit SGD: proximal Robbins-Monro vs. Polyak-Ruppert
Steerable 3D Spherical Neurons
Stochastic Contextual Dueling Bandits under Linear Stochastic Transitivity Models
Stochastic Continuous Submodular Maximization: Boosting via Non-oblivious Function
Stochastic Rising Bandits
Strategic Instrumental Variable Regression: Recovering Causal Relationships From Strategic Responses
Strategic Representation
Strategies for Safe Multi-Armed Bandits with Logarithmic Regret and Risk
Streaming Algorithm for Monotone k-Submodular Maximization with Cardinality Constraints
Streaming Algorithms for High-Dimensional Robust Statistics
Streaming Algorithms for Support-Aware Histograms
Streaming Inference for Infinite Feature Models
StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models
Structural Entropy Guided Graph Hierarchical Pooling
Structure-preserving GANs
Structure Preserving Neural Networks: A Case Study in the Entropy Closure of the Boltzmann Equation
Sublinear-Time Clustering Oracle for Signed Graphs
Subspace Learning for Effective Meta-Learning
Supervised Learning with General Risk Functionals
Supervised Off-Policy Ranking
Surrogate Likelihoods for Variational Annealed Importance Sampling
Symmetric Machine Theory of Mind
Synergy and Symmetry in Deep Learning: Interactions between the Data, Model, and Inference Algorithm
Tackling covariate shift with node-based Bayesian neural networks
Tackling Data Heterogeneity: A New Unified Framework for Decentralized SGD with Sample-induced Topology
TACTiS: Transformer-Attentional Copulas for Time Series
TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classification
Temporal Difference Learning for Model Predictive Control
The Algebraic Path Problem for Graph Metrics
The CLRS Algorithmic Reasoning Benchmark
The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks
The Complexity of k-Means Clustering when Little is Known
The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention
The dynamics of representation learning in shallow, non-linear autoencoders
The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning
The Geometry of Robust Value Functions
The Importance of Non-Markovianity in Maximum State Entropy Exploration
The Infinite Contextual Graph Markov Model
The Multivariate Community Hawkes Model for Dependent Relational Events in Continuous-time Networks
The Neural Race Reduction: Dynamics of Abstraction in Gated Networks
The Poisson Binomial Mechanism for Unbiased Federated Learning with Secure Aggregation
The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces
The power of first-order smooth optimization for black-box non-smooth problems
The Primacy Bias in Deep Reinforcement Learning
The Role of Deconfounding in Meta-learning

« prev Page 21/24 next »