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
Offline Reinforcement Learning with Value-based Episodic Memory
Off-Policy Reinforcement Learning with Delayed Rewards
Omni-Dimensional Dynamic Convolution
Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification
On Adversarial Bias and the Robustness of Fair Machine Learning
On Bridging Generic and Personalized Federated Learning for Image Classification
On Convergence of Federated Averaging Langevin Dynamics
On Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning
On Distributed Adaptive Optimization with Gradient Compression
One After Another: Learning Incremental Skills for a Changing World
One Objective for All Models --- Self-supervised Learning for Topic Models
One-Shot Generative Domain Adaptation
One Thing to Fool them All: Generating Interpretable, Universal, and Physically-Realizable Adversarial Features
On Evaluation Metrics for Graph Generative Models
On feature learning in neural networks with global convergence guarantees
On Hard Episodes in Meta-Learning
On Heterogeneously Distributed Data, Sparsity Matters
On Improving Adversarial Transferability of Vision Transformers
On Incorporating Inductive Biases into VAEs
On Invariance Penalties for Risk Minimization
On Learning to Solve Cardinality Constrained Combinatorial Optimization in One-Shot: A Re-parameterization Approach via Gumbel-Sinkhorn-TopK
Online Ad Hoc Teamwork under Partial Observability
Online Adversarial Attacks
Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference
Online Coreset Selection for Rehearsal-based Continual Learning
Online Facility Location with Predictions
Online Hyperparameter Meta-Learning with Hypergradient Distillation
Online MAP Inference and Learning for Nonsymmetric Determinantal Point Processes
Online Target Q-learning with Reverse Experience Replay: Efficiently finding the Optimal Policy for Linear MDPs
Online Tuning for Offline Decentralized Multi-Agent Reinforcement Learning
Online Unsupervised Learning of Visual Representations and Categories
On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning
On Margin Maximization in Linear and ReLU Networks
On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning
On Non-Random Missing Labels in Semi-Supervised Learning
On Optimal Early Stopping: Overparametrization versus Underparametrization
On-Policy Model Errors in Reinforcement Learning
On Predicting Generalization using GANs
On Redundancy and Diversity in Cell-based Neural Architecture Search
On Reward Maximization and Distribution Matching for Fine-Tuning Language Models
On Robust Prefix-Tuning for Text Classification
On-Target Adaptation
On the approximation properties of recurrent encoder-decoder architectures
On the benefits of deep RL in accelerated MRI sampling
On the benefits of maximum likelihood estimation for Regression and Forecasting
On the Certified Robustness for Ensemble Models and Beyond
On the Connection between Local Attention and Dynamic Depth-wise Convolution
On the Convergence of Certified Robust Training with Interval Bound Propagation
On the Convergence of mSGD and AdaGrad for Stochastic Optimization
On the Convergence of Nonconvex Continual Learning with Adaptive Learning Rate

« prev Page 31/47 next »