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
Top-k eXtreme Contextual Bandits with Arm Hierarchy
Toward Better Generalization Bounds with Locally Elastic Stability
Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing
Towards Better Robust Generalization with Shift Consistency Regularization
Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons
Towards Defending against Adversarial Examples via Attack-Invariant Features
Towards Distraction-Robust Active Visual Tracking
Towards Domain-Agnostic Contrastive Learning
Towards Open Ad Hoc Teamwork Using Graph-based Policy Learning
Towards Open-World Recommendation: An Inductive Model-based Collaborative Filtering Approach
Towards Practical Mean Bounds for Small Samples
Towards Rigorous Interpretations: a Formalisation of Feature Attribution
Towards the Unification and Robustness of Perturbation and Gradient Based Explanations
Towards Tight Bounds on the Sample Complexity of Average-reward MDPs
Towards Understanding and Mitigating Social Biases in Language Models
Towards Understanding Learning in Neural Networks with Linear Teachers
Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning
Tractable structured natural-gradient descent using local parameterizations
Training Adversarially Robust Sparse Networks via Bayesian Connectivity Sampling
Training data-efficient image transformers & distillation through attention
Training Data Subset Selection for Regression with Controlled Generalization Error
Training Graph Neural Networks with 1000 Layers
Training Quantized Neural Networks to Global Optimality via Semidefinite Programming
Training Recurrent Neural Networks via Forward Propagation Through Time
Train simultaneously, generalize better: Stability of gradient-based minimax learners
Trajectory Diversity for Zero-Shot Coordination
Transfer-Based Semantic Anomaly Detection
Trees with Attention for Set Prediction Tasks
T-SCI: A Two-Stage Conformal Inference Algorithm with Guaranteed Coverage for Cox-MLP
Two Heads are Better Than One: Hypergraph-Enhanced Graph Reasoning for Visual Event Ratiocination
Two-way kernel matrix puncturing: towards resource-efficient PCA and spectral clustering
UCB Momentum Q-learning: Correcting the bias without forgetting
Unbalanced minibatch Optimal Transport; applications to Domain Adaptation
Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies
Uncertainty Principles of Encoding GANs
Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning
Uncovering the Connections Between Adversarial Transferability and Knowledge Transferability
Understanding and Mitigating Accuracy Disparity in Regression
Understanding Failures in Out-of-Distribution Detection with Deep Generative Models
Understanding Instance-Level Label Noise: Disparate Impacts and Treatments
Understanding Invariance via Feedforward Inversion of Discriminatively Trained Classifiers
Understanding Noise Injection in GANs
Understanding self-supervised learning dynamics without contrastive pairs
Understanding the Dynamics of Gradient Flow in Overparameterized Linear models
UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning
UnICORNN: A recurrent model for learning very long time dependencies
Unified Robust Semi-Supervised Variational Autoencoder
Uniform Convergence, Adversarial Spheres and a Simple Remedy
Unifying Vision-and-Language Tasks via Text Generation
UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data

« prev Page 23/24 next »