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
On the Convergence of Projected Alternating Maximization for Equitable and Optimal Transport
On the Convergence of the Monte Carlo Exploring Starts Algorithm for Reinforcement Learning
On the Existence of Universal Lottery Tickets
On the exploitative behavior of adversarial training against adversarial attacks
On the Expressiveness and Learning of Relational Neural Networks on Hypergraphs
On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and Implications
On the Global Convergence of Gradient Descent for multi-layer ResNets in the mean-field regime
On the Impact of Client Sampling on Federated Learning Convergence
On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training
On the Implicit Biases of Architecture & Gradient Descent
On the Importance of Difficulty Calibration in Membership Inference Attacks
On the Importance of Firth Bias Reduction in Few-Shot Classification
On the interventional consistency of autoencoders
On the Latent Holes 🧀 of VAEs for Text Generation
On the Learning and Learnability of Quasimetrics
On the Limitations of Multimodal VAEs
On the One-sided Convergence of Adam-type Algorithms in Non-convex Non-concave Min-max Optimization
On the Optimal Memorization Power of ReLU Neural Networks
On the Pitfalls of Analyzing Individual Neurons in Language Models
On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks
On The Quality Assurance Of Concept-Based Representations
On the regularization landscape for the linear recommendation models
On the relation between statistical learning and perceptual distances
On the relationship between disentanglement and multi-task learning
On the Relationship between Heterophily and Robustness of Graph Neural Networks
On the Uncomputability of Partition Functions in Energy-Based Sequence Models
On the Unreasonable Effectiveness of Feature Propagation in Learning on Graphs with Missing Node Features
OntoProtein: Protein Pretraining With Gene Ontology Embedding
Open Set Domain Adaptation with Zero-shot Learning on Graph
Open-Set Recognition: A Good Closed-Set Classifier is All You Need
Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
Open-World Semi-Supervised Learning
Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networks
Optimal Representations for Covariate Shift
Optimal Transport for Causal Discovery
Optimal Transport for Long-Tailed Recognition with Learnable Cost Matrix
Optimization and Adaptive Generalization of Three layer Neural Networks
Optimization inspired Multi-Branch Equilibrium Models
Optimized Separable Convolution: Yet Another Efficient Convolution Operator
Optimizer Amalgamation
Optimizing Neural Networks with Gradient Lexicase Selection
Orchestrated Value Mapping for Reinforcement Learning
Orthogonalising gradients to speedup neural network optimisation
Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlations
OVD-Explorer: A General Information-theoretic Exploration Approach for Reinforcement Learning
Overcoming The Spectral Bias of Neural Value Approximation
PAC-Bayes Information Bottleneck
PAC Prediction Sets Under Covariate Shift
P-Adapters: Robustly Extracting Factual Information from Language Models with Diverse Prompts
Pairwise Adversarial Training for Unsupervised Class-imbalanced Domain Adaptation

« prev Page 32/47 next »