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
Avoiding Overfitting to the Importance Weights in Offline Policy Optimization
Avoiding Robust Misclassifications for Improved Robustness without Accuracy Loss
Axiomatic Explanations for Visual Search, Retrieval, and Similarity Learning
A Zest of LIME: Towards Architecture-Independent Model Distances
Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future
Backdoor Defense via Decoupling the Training Process
Back to Basics: Efficient Network Compression via IMP
BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models
Bag of Instances Aggregation Boosts Self-supervised Distillation
Balancing Average and Worst-case Accuracy in Multitask Learning
BAM: Bayes with Adaptive Memory
Bandit Learning with Joint Effect of Incentivized Sampling, Delayed Sampling Feedback, and Self-Reinforcing User Preferences
Bandwidth-based Step-Sizes for Non-Convex Stochastic Optimization
Bayesian Exploration for Lifelong Reinforcement Learning
Bayesian Framework for Gradient Leakage
Bayesian Learning with Information Gain Provably Bounds Risk for a Robust Adversarial Defense
Bayesian Modeling and Uncertainty Quantification for Learning to Optimize: What, Why, and How
Bayesian Neural Network Priors Revisited
Bayesian Relational Generative Model for Scalable Multi-modal Learning
BCDR: Betweenness Centrality-based Distance Resampling for Graph Shortest Distance Embedding
BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis
BEiT: BERT Pre-Training of Image Transformers
Benchmarking Machine Learning Robustness in Covid-19 Spike Sequence Classification
Benchmarking Sample Selection Strategies for Batch Reinforcement Learning
Benchmarking the Spectrum of Agent Capabilities
Benign Overfitting in Adversarially Robust Linear Classification
BertNet: Harvesting Knowledge Graphs from Pretrained Language Models
Best Practices in Pool-based Active Learning for Image Classification
Better Supervisory Signals by Observing Learning Paths
Beyond Examples: Constructing Explanation Space for Explaining Prototypes
Beyond Faithfulness: A Framework to Characterize and Compare Saliency Methods
Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domains
Beyond Object Recognition: A New Benchmark towards Object Concept Learning
Beyond Prioritized Replay: Sampling States in Model-Based Reinforcement Learning via Simulated Priorities
Beyond Quantization: Power aware neural networks
Beyond Target Networks: Improving Deep $Q$-learning with Functional Regularization
BiBERT: Accurate Fully Binarized BERT
Bi-linear Value Networks for Multi-goal Reinforcement Learning
BioLCNet: Reward-modulated Locally Connected Spiking Neural Networks
Bit-aware Randomized Response for Local Differential Privacy in Federated Learning
Blaschke Product Neural Networks (BPNN): A Physics-Infused Neural Network for Phase Retrieval of Meromorphic Functions
BLOOD: Bi-level Learning Framework for Out-of-distribution Generalization
Bolstering Stochastic Gradient Descent with Model Building
BoolNet: Streamlining Binary Neural Networks Using Binary Feature Maps
Boosted Curriculum Reinforcement Learning
Boosting Out-of-Distribution Detection with Multiple Pre-trained Models
Boosting Randomized Smoothing with Variance Reduced Classifiers
Boosting the Certified Robustness of L-infinity Distance Nets
Boosting the Confidence of Near-Tight Generalization Bounds for Uniformly Stable Randomized Algorithms
Bootstrapped Hindsight Experience replay with Counterintuitive Prioritization

« prev Page 5/47 next »