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
Revealing the Incentive to Cause Distributional Shift
Reverse Engineering of Imperceptible Adversarial Image Perturbations
Reversible Instance Normalization for Accurate Time-Series Forecasting against Distribution Shift
Revisiting and Advancing Fast Adversarial Training Through the lens of Bi-Level Optimization
Revisiting Design Choices in Offline Model Based Reinforcement Learning
Revisiting Embeddings for Graph Neural Networks
Revisiting flow generative models for Out-of-distribution detection
Revisiting Layer-wise Sampling in Fast Training for Graph Convolutional Networks
Revisiting Locality-Sensitive Binary Codes from Random Fourier Features
Revisiting Out-of-Distribution Detection: A Simple Baseline is Surprisingly Effective
Revisiting Over-smoothing in BERT from the Perspective of Graph
Revisiting the Lottery Ticket Hypothesis: A Ramanujan Graph Perspective
Revisiting Virtual Nodes in Graph Neural Networks for Link Prediction
Revisit Kernel Pruning with Lottery Regulated Grouped Convolutions
Reward Learning as Doubly Nonparametric Bandits: Optimal Design and Scaling Laws
Reward Shifting for Optimistic Exploration and Conservative Exploitation
Reward Uncertainty for Exploration in Preference-based Reinforcement Learning
Riemannian Manifold Embeddings for Straight-Through Estimator
RieszNet and ForestRiesz: Automatic Debiased Machine Learning with Neural Nets and Random Forests
RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimation
RL-DARTS: Differentiable Architecture Search for Reinforcement Learning
RMNet: Equivalently Removing Residual Connection from Networks
Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models
Robust and Personalized Federated Learning with Spurious Features: an Adversarial Approach
Robust and Scalable SDE Learning: A Functional Perspective
Robust Deep Neural Networks for Heterogeneous Tabular Data
Robust Generalization of Quadratic Neural Networks via Function Identification
Robust Graph Representation Learning via Predictive Coding
Robust Imitation Learning from Corrupted Demonstrations
Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?
Robust Losses for Learning Value Functions
Robust Models Are More Interpretable Because Attributions Look Normal
Robust Robotic Control from Pixels using Contrastive Recurrent State-Space Models
Robust Unlearnable Examples: Protecting Data Privacy Against Adversarial Learning
Role Diversity Matters: A Study of Cooperative Training Strategies for Multi-Agent RL
RoMA: a Method for Neural Network Robustness Measurement and Assessment
RotoGrad: Gradient Homogenization in Multitask Learning
rQdia: Regularizing Q-Value Distributions With Image Augmentation
RvS: What is Essential for Offline RL via Supervised Learning?
S3: Supervised Self-supervised Learning under Label Noise
SABAL: Sparse Approximation-based Batch Active Learning
Safe Deep RL in 3D Environments using Human Feedback
Safe Neurosymbolic Learning with Differentiable Symbolic Execution
SAFER: Data-Efficient and Safe Reinforcement Learning Through Skill Acquisition
Salient ImageNet: How to discover spurious features in Deep Learning?
SALT : Sharing Attention between Linear layer and Transformer for tabular dataset
Sample and Communication-Efficient Decentralized Actor-Critic Algorithms with Finite-Time Analysis
Sample and Computation Redistribution for Efficient Face Detection
Sample-efficient actor-critic algorithms with an etiquette for zero-sum Markov games
Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation

« prev Page 37/47 next »