ICML 2021

1,200 papers

Top Research Directions

Research directions most represented by ICML 2021 papers.

The Non-Linear Function Approximation Gap in Reinforcement Learning 26
Scaling Reinforcement Learning to High-Dimensional Visual Observations 19
Scaling Gaussian Processes Beyond Cubic Complexity 17
Clean Accuracy Degradation in Machine Learning Defenses 16
Bypassing the Computational Bottleneck of Adversarial Training 16
The Function Approximation Gap in Reinforcement Learning Theory 14
Exploration Strategies for Sparse Reward Reinforcement Learning 14
Horizon Free Bounds in Reinforcement Learning 13
Learning with Instance Dependent Label Noise 11
Variance Adaptive Confidence Bounds 11
Optimistic Exploration for Efficient Reinforcement Learning 11
Optimization and Generalization with Non-Smooth Activations 11
Accelerating Neural Architecture Search Without Full Model Training 11
Linearizing Deep Learning via the Neural Tangent Kernel 10
The Computational Overhead of Iterative Model Pruning 10

Top Authors

AuthorPapers
Masashi Sugiyama14
Sergey Levine12
Gang Niu11
Zhaoran Wang11
Zhuoran Yang11
Quanquan Gu8
Andreas Krause7
Bo Han7
Chelsea Finn7
Percy Liang7
Bernhard Schölkopf6
Csaba Szepesvari6
David Woodruff6
Michal Valko6
Pieter Abbeel6
Tongliang Liu6
Alex Dimakis5
Andrew Gordon Wilson5
Bo Li5
Gal Chechik5

Impactful Papers

Papers from ICML 2021 that shaped research clusters.

Foundational

Influential

Papers

Title
Mask wearing detection in public places based on YOLOv5
Massively Parallel and Asynchronous Tsetlin Machine Architecture Supporting Almost Constant-Time Scaling
Matrix Completion with Model-free Weighting
Matrix Sketching for Secure Collaborative Machine Learning
Maximum Mean Discrepancy Test is Aware of Adversarial Attacks
MC-LSTM: Mass-Conserving LSTM
Measuring Robustness in Deep Learning Based Compressive Sensing
Mediated Uncoupled Learning: Learning Functions without Direct Input-output Correspondences
Megaverse: Simulating Embodied Agents at One Million Experiences per Second
Memory Efficient Online Meta Learning
Memory-Efficient Pipeline-Parallel DNN Training
Message Passing Adaptive Resonance Theory for Online Active Semi-supervised Learning
Meta-Cal: Well-controlled Post-hoc Calibration by Ranking
MetaCURE: Meta Reinforcement Learning with Empowerment-Driven Exploration
Meta-Learning Bidirectional Update Rules
Meta Learning for Support Recovery in High-dimensional Precision Matrix Estimation
Meta-learning Hyperparameter Performance Prediction with Neural Processes
Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation
Meta-Thompson Sampling
Mind the Box: l1-APGD for Sparse Adversarial Attacks on Image Classifiers
Mixed Cross Entropy Loss for Neural Machine Translation
Mixed Nash Equilibria in the Adversarial Examples Game
Model-based Reinforcement Learning for Continuous Control with Posterior Sampling
Model-Based Reinforcement Learning via Latent-Space Collocation
Model Distillation for Revenue Optimization: Interpretable Personalized Pricing
Model-Free and Model-Based Policy Evaluation when Causality is Uncertain
Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity
Model Fusion for Personalized Learning
Modeling Hierarchical Structures with Continuous Recursive Neural Networks
Modelling Behavioural Diversity for Learning in Open-Ended Games
Model Performance Scaling with Multiple Data Sources
Model-Targeted Poisoning Attacks with Provable Convergence
Momentum Residual Neural Networks
Monotonic Robust Policy Optimization with Model Discrepancy
Monte Carlo Variational Auto-Encoders
Moreau-Yosida f-divergences
More Powerful and General Selective Inference for Stepwise Feature Selection using Homotopy Method
MorphVAE: Generating Neural Morphologies from 3D-Walks using a Variational Autoencoder with Spherical Latent Space
MOTS: Minimax Optimal Thompson Sampling
MSA Transformer
Muesli: Combining Improvements in Policy Optimization
Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solvers
Multi-Dimensional Classification via Sparse Label Encoding
Multidimensional Scaling: Approximation and Complexity
Multi-group Agnostic PAC Learnability
Multi-layered Network Exploration via Random Walks: From Offline Optimization to Online Learning
Multiple steps to the precipice: Risk aversion and worry in sequential decision-making
Multiplicative Noise and Heavy Tails in Stochastic Optimization
Multiplying Matrices Without Multiplying
Multirate training of neural networks

« prev Page 14/24 next »