ICLR 2022

2,337 papers

Top Research Directions

Research directions most represented by ICLR 2022 papers.

Bypassing the Computational Bottleneck of Adversarial Training 21
Sample Efficient Reinforcement Learning 19
The Mechanics of Benign Overfitting in High Dimensions 18
Clean Accuracy Degradation in Machine Learning Defenses 17
Overcoming the Homophily Assumption in Graph Neural Networks 13
Accelerating Sparse Neural Networks on Dense Hardware 13
Accelerating Neural Architecture Search Without Full Model Training 12
The Non-Linear Function Approximation Gap in Reinforcement Learning 12
The Mechanics of Backdoor Attacks in Neural Networks 12
Beyond the Lazy Training Regime of Neural Networks 11
The Infinite Width Approximation Gap in Deep Learning 10
Matrix-Free Curvature Estimation for Deep Learning 10
The Computational Overhead of Iterative Model Pruning 9
The Weisfeiler Lehman Expressivity Bottleneck 9
Why Theoretical FLOPs Fail to Predict Real Latency 9

Top Authors

AuthorPapers
Zhangyang Wang23
Sergey Levine21
Tianlong Chen15
Tongliang Liu14
Bo Han13
Chelsea Finn13
Gang Niu13
Jun Wang13
Yoshua Bengio13
Bernhard Schölkopf12
Joshua B. Tenenbaum12
J Zico Kolter12
Ping Li12
Tie-Yan Liu12
Dacheng Tao11
Stephan Günnemann11
Tom Goldstein11
Masashi Sugiyama10
Pieter Abbeel9
Pin-Yu Chen9

Impactful Papers

Papers from ICLR 2022 that shaped research clusters.

Foundational

Influential

Papers

Title
Learning Efficient and Robust Ordinary Differential Equations via Diffeomorphisms
Learning Efficient Image Super-Resolution Networks via Structure-Regularized Pruning
Learning Efficient Online 3D Bin Packing on Packing Configuration Trees
Learning Equivariances and Partial Equivariances From Data
Learning Explicit Credit Assignment for Multi-agent Joint Q-learning
Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System
Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Quality
Learning Features with Parameter-Free Layers
Learning from One and Only One Shot
Learning Generalizable Representations for Reinforcement Learning via Adaptive Meta-learner of Behavioral Similarities
Learning Global Spatial Information for Multi-View Object-Centric Models
Learning Graphon Mean Field Games and Approximate Nash Equilibria
Learning Graph Representations for Influence Maximization
Learning Graph Structure from Convolutional Mixtures
Learning Guarantees for Graph Convolutional Networks on the Stochastic Block Model
Learning Hierarchical Structures with Differentiable Nondeterministic Stacks
Learning Higher-Order Dynamics in Video-Based Cardiac Measurement
Learning Homophilic Incentives in Sequential Social Dilemmas
Learning Interpretable Dynamics from Images of a Freely Rotating 3D Rigid Body
Learning Invariant Reward Functions through Trajectory Interventions
Learning Long-Term Reward Redistribution via Randomized Return Decomposition
Learning meta-features for AutoML
Learning Minimal Representations with Model Invariance
Learning Multimodal VAEs through Mutual Supervision
Learning Neural Causal Models with Active Interventions
Learning Neural Contextual Bandits through Perturbed Rewards
Learning Neural Implicit Functions as Object Representations for Robotic Manipulation
Learning Object-Oriented Dynamics for Planning from Text
Learning Optimal Conformal Classifiers
Learning Predictive, Online Approximations of Explanatory, Offline Algorithms
Learning Prototype-oriented Set Representations for Meta-Learning
Learning Pruning-Friendly Networks via Frank-Wolfe: One-Shot, Any-Sparsity, And No Retraining
Learning Pseudometric-based Action Representations for Offline Reinforcement Learning
Learning Rate Grafting: Transferability of Optimizer Tuning
Learning Representation for Bayesian Optimization with Collision-free Regularization
Learning Representation from Neural Fisher Kernel with Low-rank Approximation
Learning Rich Nearest Neighbor Representations from Self-supervised Ensembles
Learning Robust Kernel Ensembles with Kernel Average Pooling
Learning Sample Reweighting for Adversarial Robustness
Learning Scenario Representation for Solving Two-stage Stochastic Integer Programs
Learning Similarity Metrics for Volumetric Simulations with Multiscale CNNs
Learning Stable Classifiers by Transferring Unstable Features
Learning State Representations via Retracing in Reinforcement Learning
Learning Strides in Convolutional Neural Networks
Learning Structure from the Ground up---Hierarchical Representation Learning by Chunking
Learning Super-Features for Image Retrieval
Learning Surface Parameterization for Document Image Unwarping
Learning Symmetric Representations for Equivariant World Models
Learning Synthetic Environments and Reward Networks for Reinforcement Learning
Learning Temporally Causal Latent Processes from General Temporal Data

« prev Page 24/47 next »