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
Semi-supervised Long-tailed Recognition using Alternate Sampling
Semi-supervised Offline Reinforcement Learning with Pre-trained Decision Transformers
Sequence Approximation using Feedforward Spiking Neural Network for Spatiotemporal Learning: Theory and Optimization Methods
Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learning
Sequoia: A Software Framework to Unify Continual Learning Research
SGD Can Converge to Local Maxima
SGDEM: stochastic gradient descent with energy and momentum
Shallow and Deep Networks are Near-Optimal Approximators of Korobov Functions
Shaped Rewards Bias Emergent Language
Sharper Utility Bounds for Differentially Private Models
Sharp Learning Bounds for Contrastive Unsupervised Representation Learning
ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks
Shifts 2.0: Extending The Dataset of Real Distributional Shifts
Shift-tolerant Perceptual Similarity Metric
SHINE: SHaring the INverse Estimate from the forward pass for bi-level optimization and implicit models
Short optimization paths lead to good generalization
Short-term memory in neural language models
Should I Run Offline Reinforcement Learning or Behavioral Cloning?
Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative
Should we Replace CNNs with Transformers for Medical Images?
Show Your Work: Scratchpads for Intermediate Computation with Language Models
Shuffle Private Stochastic Convex Optimization
Signing the Supermask: Keep, Hide, Invert
Simple GNN Regularisation for 3D Molecular Property Prediction and Beyond
Simpler Calibration for Survival Analysis
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
SiT: Simulation Transformer for Particle-based Physics Simulation
SketchODE: Learning neural sketch representation in continuous time
Skill-based Meta-Reinforcement Learning
SLASH: Embracing Probabilistic Circuits into Neural Answer Set Programming
SLIM-QN: A Stochastic, Light, Momentumized Quasi-Newton Optimizer for Deep Neural Networks
Soft Actor-Critic with Inhibitory Networks for Faster Retraining
SoftHebb: Bayesian inference in unsupervised Hebbian soft winner-take-all networks
Solving Inverse Problems in Medical Imaging with Score-Based Generative Models
SOSP: Efficiently Capturing Global Correlations by Second-Order Structured Pruning
Soteria: In search of efficient neural networks for private inference
Sound Adversarial Audio-Visual Navigation
Sound and Complete Neural Network Repair with Minimality and Locality Guarantees
Sound Source Detection from Raw Waveforms with Multi-Scale Synperiodic Filterbanks
Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration
Source-Target Unified Knowledge Distillation for Memory-Efficient Federated Domain Adaptation on Edge Devices
Space-Time Graph Neural Networks
SpanDrop: Simple and Effective Counterfactual Learning for Long Sequences
Spanning Tree-based Graph Generation for Molecules
SPARK: co-exploring model SPArsity and low-RanKness for compact neural networks
Sparse Attention with Learning to Hash
Sparse Communication via Mixed Distributions
Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity
Sparse MoEs meet Efficient Ensembles
Sparsity Winning Twice: Better Robust Generalization from More Efficient Training

« prev Page 39/47 next »