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
Test-Time Adaptation to Distribution Shifts by Confidence Maximization and Input Transformation
Test-time Batch Statistics Calibration for Covariate Shift
Test Time Robustification of Deep Models via Adaptation and Augmentation
Text-Driven Image Manipulation via Semantic-Aware Knowledge Transfer
Text Generation with Efficient (Soft) $Q$-Learning
Text Style Transfer with Confounders
That Escalated Quickly: Compounding Complexity by Editing Levels at the Frontier of Agent Capabilities
The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models
The Challenges of Exploration for Offline Reinforcement Learning
The Close Relationship Between Contrastive Learning and Meta-Learning
The Connection between Out-of-Distribution Generalization and Privacy of ML Models
The Convex Geometry of Backpropagation: Neural Network Gradient Flows Converge to Extreme Points of the Dual Convex Program
The Curse of Low Task Diversity: On the Failure of Transfer Learning to Outperform MAML and Their Empirical Equivalence
The Effect of diversity in Meta-Learning
The Effects of Invertibility on the Representational Complexity of Encoders in Variational Autoencoders
The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models
The Efficiency Misnomer
The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning
The Evolution of Uncertainty of Learning in Games
The Geometry of Adversarial Subspaces
The Geometry of Memoryless Stochastic Policy Optimization in Infinite-Horizon POMDPs
The guide and the explorer: smart agents for resource-limited iterated batch reinforcement learning
The Hidden Convex Optimization Landscape of Regularized Two-Layer ReLU Networks: an Exact Characterization of Optimal Solutions
The hidden label-marginal biases of segmentation losses
The Inductive Bias of In-Context Learning: Rethinking Pretraining Example Design
The Information Geometry of Unsupervised Reinforcement Learning
The magnitude vector of images
The Manifold Hypothesis for Gradient-Based Explanations
The MultiBERTs: BERT Reproductions for Robustness Analysis
The Needle in the haystack: Out-distribution aware Self-training in an Open-World Setting
The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization
The NTK Adversary: An Approach to Adversarial Attacks without any Model Access
Theoretical Analysis of Consistency Regularization with Limited Augmented Data
The Power of Contrast for Feature Learning: A Theoretical Analysis
The Remarkable Effectiveness of Combining Policy and Value Networks in A*-based Deep RL for AI Planning
The Rich Get Richer: Disparate Impact of Semi-Supervised Learning
The Role of Learning Regime, Architecture and Dataset Structure on Systematic Generalization in Simple Neural Networks
The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks
The Role of Pretrained Representations for the OOD Generalization of RL Agents
The Spectral Bias of Polynomial Neural Networks
The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022
The Three Stages of Learning Dynamics in High-dimensional Kernel Methods
The Uncanny Similarity of Recurrence and Depth
The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training
The weighted mean trick – optimization strategies for robustness
Thinking Deeper With Recurrent Networks: Logical Extrapolation Without Overthinking
THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling
Tighter Sparse Approximation Bounds for ReLU Neural Networks
Tight lower bounds for Differentially Private ERM
To Impute or Not To Impute? Missing Data in Treatment Effect Estimation

« prev Page 42/47 next »