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
A Sampling-Free Approximation of Gaussian Variational Auto-Encoders
A Scaling Law for Syn-to-Real Transfer: How Much Is Your Pre-training Effective?
A Simple and Debiased Sampling Method for Personalized Ranking
A Simple Approach to Adversarial Robustness in Few-shot Image Classification
Ask2Mask: Guided Data Selection for Masked Speech Modeling
AS-MLP: An Axial Shifted MLP Architecture for Vision
Assessing Generalization of SGD via Disagreement
Associated Learning: an Alternative to End-to-End Backpropagation that Works on CNN, RNN, and Transformer
A Statistical Framework for Efficient Out of Distribution Detection in Deep Neural Networks
A Survey on Evidential Deep Learning For Single-Pass Uncertainty Estimation
Asymmetry Learning for Counterfactually-invariant Classification in OOD Tasks
Asynchronous Multi-Agent Actor-Critic with Macro-Actions
A Systematic Evaluation of Domain Adaptation Algorithms On Time Series Data
A Tale of Two Flows: Cooperative Learning of Langevin Flow and Normalizing Flow Toward Energy-Based Model
A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features
A Theoretical and Empirical Model of the Generalization Error under Time-Varying Learning Rate
A theoretically grounded characterization of feature representations
A Theory of Tournament Representations
A Topological View of Rule Learning in Knowledge Graphs
Attacking deep networks with surrogate-based adversarial black-box methods is easy
Attend to Who You Are: Supervising Self-Attention for Keypoint Detection and Instance-Aware Association
Attentional meta-learners for few-shot polythetic classification
Attention-based Interpretability with Concept Transformers
Attention: Self-Expression Is All You Need
Audio Lottery: Speech Recognition Made Ultra-Lightweight, Noise-Robust, and Transferable
Auditing AI models for Verified Deployment under Semantic Specifications
Aug-ILA: More Transferable Intermediate Level Attacks with Augmented References
Augmentative Topology Agents For Open-Ended Learning
Augmented Sliced Wasserstein Distances
A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training
A Unified Knowledge Distillation Framework for Deep Directed Graphical Models
A Unified Wasserstein Distributional Robustness Framework for Adversarial Training
Auto-Encoding Inverse Reinforcement Learning
Automated Mobile Attention KPConv Networks via A Wide & Deep Predictor
Automated Self-Supervised Learning for Graphs
Automatic Concept Extraction for Concept Bottleneck-based Video Classification
Automatic Forecasting via Meta-Learning
Automatic Loss Function Search for Predict-Then-Optimize Problems with Strong Ranking Property
Automatic prior selection for meta Bayesian optimization with a case study on tuning deep neural network optimizers
AutoNF: Automated Architecture Optimization of Normalizing Flows Using a Mixture Distribution Formulation
Autonomous Learning of Object-Centric Abstractions for High-Level Planning
Autonomous Reinforcement Learning: Formalism and Benchmarking
AutoOED: Automated Optimal Experimental Design Platform with Data- and Time-Efficient Multi-Objective Optimization
Autoregressive Diffusion Models
Autoregressive Latent Video Prediction with High-Fidelity Image Generator
Autoregressive Quantile Flows for Predictive Uncertainty Estimation
Auto-scaling Vision Transformers without Training
Auto-Transfer: Learning to Route Transferable Representations
A Variance Principle Explains why Dropout Finds Flatter Minima
A Variance Reduction Method for Neural-based Divergence Estimation

« prev Page 4/47 next »