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
Learning to Separate Voices by Spatial Regions
Learning to Solve PDE-constrained Inverse Problems with Graph Networks
Least Squares Estimation using Sketched Data with Heteroskedastic Errors
LeNSE: Learning To Navigate Subgraph Embeddings for Large-Scale Combinatorial Optimisation
Let Invariant Rationale Discovery Inspire Graph Contrastive Learning
Leverage Score Sampling for Tensor Product Matrices in Input Sparsity Time
LIDL: Local Intrinsic Dimension Estimation Using Approximate Likelihood
Lie Point Symmetry Data Augmentation for Neural PDE Solvers
Lightweight Projective Derivative Codes for Compressed Asynchronous Gradient Descent
LIMO: Latent Inceptionism for Targeted Molecule Generation
Linear Adversarial Concept Erasure
Linear Bandit Algorithms with Sublinear Time Complexity
Linear Complexity Randomized Self-attention Mechanism
Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness
Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costs
Local Augmentation for Graph Neural Networks
Local Linear Convergence of Douglas-Rachford for Linear Programming: a Probabilistic Analysis
Locally Sparse Neural Networks for Tabular Biomedical Data
Log-Euclidean Signatures for Intrinsic Distances Between Unaligned Datasets
Loss Function Learning for Domain Generalization by Implicit Gradient
Low-Complexity Deep Convolutional Neural Networks on Fully Homomorphic Encryption Using Multiplexed Parallel Convolutions
LSB: Local Self-Balancing MCMC in Discrete Spaces
LyaNet: A Lyapunov Framework for Training Neural ODEs
Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control
MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection
Making Linear MDPs Practical via Contrastive Representation Learning
MAML and ANIL Provably Learn Representations
Marginal Distribution Adaptation for Discrete Sets via Module-Oriented Divergence Minimization
Markov Chain Monte Carlo for Continuous-Time Switching Dynamical Systems
MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay Buffer
Maslow's Hammer in Catastrophic Forgetting: Node Re-Use vs. Node Activation
Massively Parallel k-Means Clustering for Perturbation Resilient Instances
Matching Learned Causal Effects of Neural Networks with Domain Priors
Matching Normalizing Flows and Probability Paths on Manifolds
Matching Structure for Dual Learning
Maximum Likelihood Training for Score-based Diffusion ODEs by High Order Denoising Score Matching
Meaningfully debugging model mistakes using conceptual counterfactual explanations
Measure Estimation in the Barycentric Coding Model
Measuring dissimilarity with diffeomorphism invariance
Measuring Representational Robustness of Neural Networks Through Shared Invariances
Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments
ME-GAN: Learning Panoptic Electrocardio Representations for Multi-view ECG Synthesis Conditioned on Heart Diseases
Memory-Based Model Editing at Scale
MemSR: Training Memory-efficient Lightweight Model for Image Super-Resolution
Meta-Learning Hypothesis Spaces for Sequential Decision-making
MetAug: Contrastive Learning via Meta Feature Augmentation
Metric-Fair Active Learning
Metric-Fair Classifier Derandomization
Minimax Classification under Concept Drift with Multidimensional Adaptation and Performance Guarantees
Minimax M-estimation under Adversarial Contamination

« prev Page 13/24 next »