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
Understanding and Leveraging Overparameterization in Recursive Value Estimation
Understanding and Preventing Capacity Loss in Reinforcement Learning
Understanding and Scheduling Weight Decay
Understanding approximate and unrolled dictionary learning for pattern recovery
Understanding Dimensional Collapse in Contrastive Self-supervised Learning
Understanding Domain Randomization for Sim-to-real Transfer
Understanding Generalized Label Smoothing when Learning with Noisy Labels
Understanding Graph Learning with Local Intrinsic Dimensionality
Understanding Intrinsic Robustness Using Label Uncertainty
Understanding Knowledge Integration in Language Models with Graph Convolutions
Understanding Latent Correlation-Based Multiview Learning and Self-Supervision: An Identifiability Perspective
Understanding Metric Learning on Unit Hypersphere and Generating Better Examples for Adversarial Training
Understanding Overfitting in Reweighting Algorithms for Worst-group Performance
Understanding over-squashing and bottlenecks on graphs via curvature
Understanding Sharpness-Aware Minimization
Understanding the Generalization Gap in Visual Reinforcement Learning
Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization
Understanding the Interaction of Adversarial Training with Noisy Labels
Understanding the Role of Self Attention for Efficient Speech Recognition
Understanding the Success of Knowledge Distillation -- A Data Augmentation Perspective
Understanding the Variance Collapse of SVGD in High Dimensions
Unified Recurrence Modeling for Video Action Anticipation
Unified Visual Transformer Compression
UniFormer: Unified Transformer for Efficient Spatial-Temporal Representation Learning
Uniform Generalization Bounds for Overparameterized Neural Networks
Unifying Categorical Models by Explicit Disentanglement of the Labels' Generative Factors
Unifying Distribution Alignment as a Loss for Imbalanced Semi-supervised Learning
Unifying Likelihood-free Inference with Black-box Optimization and Beyond
Unit Ball Model for Embedding Hierarchical Structures in the Complex Hyperbolic Space
Universal Approximation Under Constraints is Possible with Transformers
Universal Controllers with Differentiable Physics for Online System Identification
Universality of Deep Neural Network Lottery Tickets: A Renormalization Group Perspective
Universalizing Weak Supervision
Universal Joint Approximation of Manifolds and Densities by Simple Injective Flows
Universal Mini-Batch Consistency for Set Encoding Functions
Unraveling Model-Agnostic Meta-Learning via The Adaptation Learning Rate
Unrolling PALM for Sparse Semi-Blind Source Separation
Unsupervised Discovery of Object Radiance Fields
Unsupervised Disentanglement with Tensor Product Representations on the Torus
Unsupervised Learning of Full-Waveform Inversion: Connecting CNN and Partial Differential Equation in a Loop
Unsupervised Neural Machine Translation with Generative Language Models Only
Unsupervised Object Learning via Common Fate
Unsupervised Pose-Aware Part Decomposition for 3D Articulated Objects
Unsupervised Semantic Segmentation by Distilling Feature Correspondences
Unsupervised Vision-Language Grammar Induction with Shared Structure Modeling
Using Document Similarity Methods to create Parallel Datasets for Code Translation
Using Graph Representation Learning with Schema Encoders to Measure the Severity of Depressive Symptoms
VAE Approximation Error: ELBO and Exponential Families
Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning
Value Gradient weighted Model-Based Reinforcement Learning

« prev Page 45/47 next »