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
Dataset Condensation with Contrastive Signals
Data-SUITE: Data-centric identification of in-distribution incongruous examples
DAVINZ: Data Valuation using Deep Neural Networks at Initialization
Debiaser Beware: Pitfalls of Centering Regularized Transport Maps
Decentralized Online Convex Optimization in Networked Systems
Deciphering Lasso-based Classification Through a Large Dimensional Analysis of the Iterative Soft-Thresholding Algorithm
Decision-Focused Learning: Through the Lens of Learning to Rank
Decomposing Temporal High-Order Interactions via Latent ODEs
Deconfounded Value Decomposition for Multi-Agent Reinforcement Learning
Deduplicating Training Data Mitigates Privacy Risks in Language Models
Deep and Flexible Graph Neural Architecture Search
Deep Causal Metric Learning
Deep equilibrium networks are sensitive to initialization statistics
Deep Hierarchy in Bandits
Deep Network Approximation in Terms of Intrinsic Parameters
Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry
Deep Neural Network Fusion via Graph Matching with Applications to Model Ensemble and Federated Learning
Deep Safe Incomplete Multi-view Clustering: Theorem and Algorithm
DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale
Deep Squared Euclidean Approximation to the Levenshtein Distance for DNA Storage
Deep symbolic regression for recurrence prediction
Deep Variational Graph Convolutional Recurrent Network for Multivariate Time Series Anomaly Detection
Delay-Adaptive Step-sizes for Asynchronous Learning
Delayed Reinforcement Learning by Imitation
Deletion Robust Submodular Maximization over Matroids
Demystifying the Adversarial Robustness of Random Transformation Defenses
Denoised MDPs: Learning World Models Better Than the World Itself
De novo mass spectrometry peptide sequencing with a transformer model
Deploying Convolutional Networks on Untrusted Platforms Using 2D Holographic Reduced Representations
DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks
Describing Differences between Text Distributions with Natural Language
Design and implementation of a dual-feature fusion target tracking detection system based on Python Productivity for ZYNQ
Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization
Detached Error Feedback for Distributed SGD with Random Sparsification
Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Them
Detecting Corrupted Labels Without Training a Model to Predict
Dialog Inpainting: Turning Documents into Dialogs
Difference Advantage Estimation for Multi-Agent Policy Gradients
Differentiable Top-k Classification Learning
Differentially Private Approximate Quantiles
Differentially Private Community Detection for Stochastic Block Models
Differentially Private Coordinate Descent for Composite Empirical Risk Minimization
Differentially Private Maximal Information Coefficients
Diffusion bridges vector quantized variational autoencoders
Diffusion Models for Adversarial Purification
Dimension-free Complexity Bounds for High-order Nonconvex Finite-sum Optimization
Direct Behavior Specification via Constrained Reinforcement Learning
Directed Acyclic Transformer for Non-Autoregressive Machine Translation
Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning
Discrete Probabilistic Inverse Optimal Transport

« prev Page 6/24 next »