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
Conditioning Sequence-to-sequence Networks with Learned Activations
ConFeSS: A Framework for Single Source Cross-Domain Few-Shot Learning
Confidence-aware Training of Smoothed Classifiers for Certified Robustness
Confident Sinkhorn Allocation for Pseudo-Labeling
Conjugation Invariant Learning with Neural Networks
Connecting Graph Convolution and Graph PCA
Connectivity Matters: Neural Network Pruning Through the Lens of Effective Sparsity
Connectome-constrained Latent Variable Model of Whole-Brain Neural Activity
Consistent Counterfactuals for Deep Models
Constant-Factor Approximation Algorithms for Socially Fair $k$-Clustering
Constrained Discrete Black-Box Optimization using Mixed-Integer Programming
Constrained Physical-Statistics Models for Dynamical System Identification and Prediction
Constrained Policy Optimization via Bayesian World Models
Constraining Linear-chain CRFs to Regular Languages
Constructing a Good Behavior Basis for Transfer using Generalized Policy Updates
Constructing Orthogonal Convolutions in an Explicit Manner
Contact Points Discovery for Soft-Body Manipulations with Differentiable Physics
Containerized Distributed Value-Based Multi-Agent Reinforcement Learning
Context-Aware Sparse Deep Coordination Graphs
Context-invariant, multi-variate time series representations
Contextualized Scene Imagination for Generative Commonsense Reasoning
Contextual Multi-Armed Bandit with Communication Constraints
Continual Backprop: Stochastic Gradient Descent with Persistent Randomness
Continual Learning in Deep Networks: an Analysis of the Last Layer
Continual Learning Using Task Conditional Neural Networks
Continual Learning with Filter Atom Swapping
Continual Learning with Recursive Gradient Optimization
Continual Normalization: Rethinking Batch Normalization for Online Continual Learning
Continuous Control with Action Quantization from Demonstrations
Continuous Control With Ensemble Deep Deterministic Policy Gradients
Continuously Discovering Novel Strategies via Reward-Switching Policy Optimization
Continuous-Time Meta-Learning with Forward Mode Differentiation
Contractive error feedback for gradient compression
ContraQA: Question Answering under Contradicting Contexts
Contrastive Attraction and Contrastive Repulsion for Representation Learning
Contrastive Clustering to Mine Pseudo Parallel Data for Unsupervised Translation
Contrastive Fine-grained Class Clustering via Generative Adversarial Networks
Contrastive Learning of 3D Shape Descriptor with Dynamic Adversarial Views
Contrastive Mutual Information Maximization for Binary Neural Networks
Contrastive Pre-training for Zero-Shot Information Retrieval
Contrastive Representation Learning for 3D Protein Structures
Controlling Directions Orthogonal to a Classifier
Controlling the Complexity and Lipschitz Constant improves Polynomial Nets
Convergence Analysis and Implicit Regularization of Feedback Alignment for Deep Linear Networks
Convergent and Efficient Deep Q Learning Algorithm
Convergent Graph Solvers
Convolutional Neural Network Dynamics: A Graph Perspective
Coordination Among Neural Modules Through a Shared Global Workspace
CoordX: Accelerating Implicit Neural Representation with a Split MLP Architecture
COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks

« prev Page 8/47 next »