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
Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential Recommendation
Learning Stochastic Behaviour from Aggregate Data
Learning Task Informed Abstractions
Learning to Generate Noise for Multi-Attack Robustness
Learning to Price Against a Moving Target
Learning to Rehearse in Long Sequence Memorization
Learning to Weight Imperfect Demonstrations
Learning Transferable Visual Models From Natural Language Supervision
Learning While Playing in Mean-Field Games: Convergence and Optimality
Learn-to-Share: A Hardware-friendly Transfer Learning Framework Exploiting Computation and Parameter Sharing
LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs
Lenient Regret and Good-Action Identification in Gaussian Process Bandits
Let's Agree to Degree: Comparing Graph Convolutional Networks in the Message-Passing Framework
Leveraged Weighted Loss for Partial Label Learning
Leveraging Good Representations in Linear Contextual Bandits
Leveraging Language to Learn Program Abstractions and Search Heuristics
Leveraging Machine Learning for Equitable Transition of Energy Systems
Leveraging Non-uniformity in First-order Non-convex Optimization
Leveraging Public Data for Practical Private Query Release
Leveraging Sparse Linear Layers for Debuggable Deep Networks
LieTransformer: Equivariant Self-Attention for Lie Groups
Light RUMs
LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning
Linear Transformers Are Secretly Fast Weight Programmers
Link Prediction with Persistent Homology: An Interactive View
Lipschitz normalization for self-attention layers with application to graph neural networks
Local Algorithms for Finding Densely Connected Clusters
Local Correlation Clustering with Asymmetric Classification Errors
Locally Adaptive Label Smoothing Improves Predictive Churn
Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards
Locally Private k-Means in One Round
Logarithmic Regret for Reinforcement Learning with Linear Function Approximation
LogME: Practical Assessment of Pre-trained Models for Transfer Learning
Lossless Compression of Efficient Private Local Randomizers
Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling
Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?
Lower-Bounded Proper Losses for Weakly Supervised Classification
Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries
Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision
Low-Rank Sinkhorn Factorization
LTL2Action: Generalizing LTL Instructions for Multi-Task RL
Machine learning analysis and inference of student performance and visualization of data results based on a small dataset of student information
Machine Unlearning for Random Forests
Making Paper Reviewing Robust to Bid Manipulation Attacks
Making transport more robust and interpretable by moving data through a small number of anchor points
Mandoline: Model Evaluation under Distribution Shift
Marginal Contribution Feature Importance - an Axiomatic Approach for Explaining Data
Marginalized Stochastic Natural Gradients for Black-Box Variational Inference
MARINA: Faster Non-Convex Distributed Learning with Compression
Markpainting: Adversarial Machine Learning meets Inpainting

« prev Page 13/24 next »