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
Quantifying and Reducing Bias in Maximum Likelihood Estimation of Structured Anomalies
Quantifying Availability and Discovery in Recommender Systems via Stochastic Reachability
Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels
Quantile Bandits for Best Arms Identification
Quantitative Understanding of VAE as a Non-linearly Scaled Isometric Embedding
Quantization Algorithms for Random Fourier Features
Quantum algorithms for reinforcement learning with a generative model
Quasi-global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data
Query Complexity of Adversarial Attacks
Randomized Algorithms for Submodular Function Maximization with a k-System Constraint
Randomized Dimensionality Reduction for Facility Location and Single-Linkage Clustering
Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning
Randomized Exploration in Reinforcement Learning with General Value Function Approximation
Rate-Distortion Analysis of Minimum Excess Risk in Bayesian Learning
Real-Scenes Face Super-Resolution using a Lightweight Generative Adversarial Network
Recomposing the Reinforcement Learning Building Blocks with Hypernetworks
Reconstruction of Long-Term Historical Electricity Demand Data
Recovering AES Keys with a Deep Cold Boot Attack
Regret and Cumulative Constraint Violation Analysis for Online Convex Optimization with Long Term Constraints
Regret Minimization in Stochastic Non-Convex Learning via a Proximal-Gradient Approach
Regularized Online Allocation Problems: Fairness and Beyond
Regularized Submodular Maximization at Scale
Regularizing towards Causal Invariance: Linear Models with Proxies
Reinforcement Learning for Cost-Aware Markov Decision Processes
Reinforcement Learning of Implicit and Explicit Control Flow Instructions
Reinforcement Learning Under Moral Uncertainty
Relative Deviation Margin Bounds
Relative Positional Encoding for Transformers with Linear Complexity
REPAINT: Knowledge Transfer in Deep Reinforcement Learning
Representational aspects of depth and conditioning in normalizing flows
Representation Matters: Assessing the Importance of Subgroup Allocations in Training Data
Representation Matters: Offline Pretraining for Sequential Decision Making
Representation Subspace Distance for Domain Adaptation Regression
Research on Automatic Online Analysis Method of Data Hotness in Big Data Scenario
Research on Medical Image Segmentation Method
Research on the Defogging Algorithm Based on Image Enhancement
Reserve Price Optimization for First Price Auctions in Display Advertising
Resource Allocation in Multi-armed Bandit Exploration: Overcoming Sublinear Scaling with Adaptive Parallelism
Rethinking Neural vs. Matrix-Factorization Collaborative Filtering: the Theoretical Perspectives
Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss
Re-understanding Finite-State Representations of Recurrent Policy Networks
Revealing the Structure of Deep Neural Networks via Convex Duality
Revenue-Incentive Tradeoffs in Dynamic Reserve Pricing
Revisiting Peng's Q(λ) for Modern Reinforcement Learning
Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline
Revisiting Rainbow: Promoting more insightful and inclusive deep reinforcement learning research
Reward Identification in Inverse Reinforcement Learning
Riemannian Convex Potential Maps
Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning
Risk-Sensitive Reinforcement Learning with Function Approximation: A Debiasing Approach

« prev Page 19/24 next »