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
Prototypical Contrastive Predictive Coding
Provable Adaptation across Multiway Domains via Representation Learning
Provable Federated Adversarial Learning via Min-max Optimization
Provable hierarchical lifelong learning with a sketch-based modular architecture
Provable Hierarchy-Based Meta-Reinforcement Learning
Provable Learning-based Algorithm For Sparse Recovery
Provable Learning of Convolutional Neural Networks with Data Driven Features
Provably Calibrated Regression Under Distribution Drift
Provably convergent quasistatic dynamics for mean-field two-player zero-sum games
Provably Filtering Exogenous Distractors using Multistep Inverse Dynamics
Provably Improved Context-Based Offline Meta-RL with Attention and Contrastive Learning
Provably Robust Adversarial Examples
Provably Robust Detection of Out-of-distribution Data (almost) for free
Proving the Lottery Ticket Hypothesis for Convolutional Neural Networks
Pruning by Active Attention Manipulation
Pruning Compact ConvNets For Efficient Inference
PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series
Pseudo Knowledge Distillation: Towards Learning Optimal Instance-specific Label Smoothing Regularization
Pseudo-Labeled Auto-Curriculum Learning for Semi-Supervised Keypoint Localization
Pseudo Numerical Methods for Diffusion Models on Manifolds
Public Data-Assisted Mirror Descent for Private Model Training
Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and Forecasting
QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization
QTN-VQC: An End-to-End Learning Framework for Quantum Neural Networks
Quadtree Attention for Vision Transformers
Quantifying the Controllability of Coarsely Characterized Networked Dynamical Systems
Quantitative Performance Assessment of CNN Units via Topological Entropy Calculation
Quantized sparse PCA for neural network weight compression
Quasi-Newton policy gradient algorithms
Quasi-potential theory for escape problem: Quantitative sharpness effect on SGD's escape from local minima
QUERY EFFICIENT DECISION BASED SPARSE ATTACKS AGAINST BLACK-BOX DEEP LEARNING MODELS
Query Embedding on Hyper-Relational Knowledge Graphs
QUIC-FL: : Quick Unbiased Compression for Federated Learning
R4D: Utilizing Reference Objects for Long-Range Distance Estimation
R5: Rule Discovery with Reinforced and Recurrent Relational Reasoning
RainNet: A Large-Scale Imagery Dataset for Spatial Precipitation Downscaling
Randomized Primal-Dual Coordinate Method for Large-scale Linearly Constrained Nonsmooth Nonconvex Optimization
Randomized Signature Layers for Signal Extraction in Time Series Data
Random matrices in service of ML footprint: ternary random features with no performance loss
RAR: Region-Aware Point Cloud Registration
Reachability Traces for Curriculum Design in Reinforcement Learning
Real-Time Neural Voice Camouflage
Reasoning-Modulated Representations
Reasoning With Hierarchical Symbols: Reclaiming Symbolic Policies For Visual Reinforcement Learning
Recognizing and overcoming the greedy nature of learning in multi-modal deep neural networks
Recurrent Model-Free RL is a Strong Baseline for Many POMDPs
Recurrent Parameter Generators
Recursive Construction of Stable Assemblies of Recurrent Neural Networks
Recursive Disentanglement Network
Recycling Model Updates in Federated Learning: Are Gradient Subspaces Low-Rank?

« prev Page 35/47 next »