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
OmniNet: Omnidirectional Representations from Transformers
On a Combination of Alternating Minimization and Nesterov's Momentum
On Characterizing GAN Convergence Through Proximal Duality Gap
On Disentangled Representations Learned from Correlated Data
One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning
On Energy-Based Models with Overparametrized Shallow Neural Networks
One Pass Late Fusion Multi-view Clustering
Oneshot Differentially Private Top-k Selection
One-sided Frank-Wolfe algorithms for saddle problems
On Estimation in Latent Variable Models
On Explainability of Graph Neural Networks via Subgraph Explorations
On Learnability via Gradient Method for Two-Layer ReLU Neural Networks in Teacher-Student Setting
On Limited-Memory Subsampling Strategies for Bandits
Online A-Optimal Design and Active Linear Regression
On Linear Identifiability of Learned Representations
Online Graph Dictionary Learning
Online Learning for Load Balancing of Unknown Monotone Resource Allocation Games
Online Learning in Unknown Markov Games
Online Learning with Optimism and Delay
Online Limited Memory Neural-Linear Bandits with Likelihood Matching
Online Optimization in Games via Control Theory: Connecting Regret, Passivity and Poincaré Recurrence
Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with $\sqrt$T Regret
Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with √T Regret
Online Selection Problems against Constrained Adversary
Online Submodular Resource Allocation with Applications to Rebalancing Shared Mobility Systems
Online Unrelated Machine Load Balancing with Predictions Revisited
On Lower Bounds for Standard and Robust Gaussian Process Bandit Optimization
On Monotonic Linear Interpolation of Neural Network Parameters
On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classification
On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework
On-Policy Deep Reinforcement Learning for the Average-Reward Criterion
On Proximal Policy Optimization's Heavy-tailed Gradients
On Reinforcement Learning with Adversarial Corruption and Its Application to Block MDP
On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game
On Robust Mean Estimation under Coordinate-level Corruption
On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes
On the Convergence of Hamiltonian Monte Carlo with Stochastic Gradients
On the difficulty of unbiased alpha divergence minimization
On the Explicit Role of Initialization on the Convergence and Implicit Bias of Overparametrized Linear Networks
On-the-fly Rectification for Robust Large-Vocabulary Topic Inference
On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel Models
On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent
On the Inherent Regularization Effects of Noise Injection During Training
On the Optimality of Batch Policy Optimization Algorithms
On the Power of Localized Perceptron for Label-Optimal Learning of Halfspaces with Adversarial Noise
On the Predictability of Pruning Across Scales
On the price of explainability for some clustering problems
On the Problem of Underranking in Group-Fair Ranking
On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths
On the Random Conjugate Kernel and Neural Tangent Kernel

« prev Page 16/24 next »