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
Blocks Assemble! Learning to Assemble with Large-Scale Structured Reinforcement Learning
Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness
Boosting Graph Structure Learning with Dummy Nodes
Born-Infeld (BI) for AI: Energy-Conserving Descent (ECD) for Optimization
Bounding the Width of Neural Networks via Coupled Initialization A Worst Case Analysis
Bounding Training Data Reconstruction in Private (Deep) Learning
Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding
Branching Reinforcement Learning
Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities
Breaking the $\sqrt{T}$ Barrier: Instance-Independent Logarithmic Regret in Stochastic Contextual Linear Bandits
Bregman Neural Networks
Bregman Power k-Means for Clustering Exponential Family Data
Bregman Proximal Langevin Monte Carlo via Bregman-Moreau Envelopes
Building Robust Ensembles via Margin Boosting
Burst-Dependent Plasticity and Dendritic Amplification Support Target-Based Learning and Hierarchical Imitation Learning
ButterflyFlow: Building Invertible Layers with Butterfly Matrices
Byzantine Machine Learning Made Easy By Resilient Averaging of Momentums
C*-algebra Net: A New Approach Generalizing Neural Network Parameters to C*-algebra
Calibrated and Sharp Uncertainties in Deep Learning via Density Estimation
Calibrated Learning to Defer with One-vs-All Classifiers
Cascaded Gaps: Towards Logarithmic Regret for Risk-Sensitive Reinforcement Learning
Causal Conceptions of Fairness and their Consequences
Causal Dynamics Learning for Task-Independent State Abstraction
Causal Imitation Learning under Temporally Correlated Noise
Causal Inference Through the Structural Causal Marginal Problem
Causal structure-based root cause analysis of outliers
Causal Transformer for Estimating Counterfactual Outcomes
Centroid Approximation for Bootstrap: Improving Particle Quality at Inference
CerDEQ: Certifiable Deep Equilibrium Model
Certified Adversarial Robustness Under the Bounded Support Set
Certified Neural Network Watermarks with Randomized Smoothing
Certified Robustness Against Natural Language Attacks by Causal Intervention
Certifying Out-of-Domain Generalization for Blackbox Functions
Channel exchange network model for house price prediction
Channel Importance Matters in Few-Shot Image Classification
Characterizing and Overcoming the Greedy Nature of Learning in Multi-modal Deep Neural Networks
Choosing Answers in Epsilon-Best-Answer Identification for Linear Bandits
CITRIS: Causal Identifiability from Temporal Intervened Sequences
Classification Method of Surface Defects of Aluminum Profile Based on Transfer Learning
Class-Imbalanced Semi-Supervised Learning with Adaptive Thresholding
Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning Environments
Closed-Form Diffeomorphic Transformations for Time Series Alignment
Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets
COAT: Measuring Object Compositionality in Emergent Representations
Coin Flipping Neural Networks
Communication-Efficient Adaptive Federated Learning
Communication-efficient Distributed Learning for Large Batch Optimization
Comparison Of Different Machine Learning Methods Applied To Obesity Classification
Composing Partial Differential Equations with Physics-Aware Neural Networks
Comprehensive Analysis of Negative Sampling in Knowledge Graph Representation Learning

« prev Page 4/24 next »