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
Federated Continual Learning with Weighted Inter-client Transfer
Federated Deep AUC Maximization for Hetergeneous Data with a Constant Communication Complexity
Federated Learning of User Verification Models Without Sharing Embeddings
Federated Learning under Arbitrary Communication Patterns
Few-Shot Conformal Prediction with Auxiliary Tasks
Few-shot Language Coordination by Modeling Theory of Mind
Few-Shot Neural Architecture Search
FILTRA: Rethinking Steerable CNN by Filter Transform
Finding k in Latent k- polytope
Finding Relevant Information via a Discrete Fourier Expansion
Finding the Stochastic Shortest Path with Low Regret: the Adversarial Cost and Unknown Transition Case
Finite mixture models do not reliably learn the number of components
Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm
First-Order Methods for Wasserstein Distributionally Robust MDP
Fixed-Parameter and Approximation Algorithms for PCA with Outliers
FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Analysis
Flow-based Attribution in Graphical Models: A Recursive Shapley Approach
Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design
Follow-the-Regularized-Leader Routes to Chaos in Routing Games
FOP: Factorizing Optimal Joint Policy of Maximum-Entropy Multi-Agent Reinforcement Learning
From Local Structures to Size Generalization in Graph Neural Networks
From Local to Global Norm Emergence: Dissolving Self-reinforcing Substructures with Incremental Social Instruments
From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization
Functional Space Analysis of Local GAN Convergence
Function Contrastive Learning of Transferable Meta-Representations
Fundamental Tradeoffs in Distributionally Adversarial Training
Fused Acoustic and Text Encoding for Multimodal Bilingual Pretraining and Speech Translation
GANMEX: One-vs-One Attributions using GAN-based Model Explainability
Gaussian Process-Based Real-Time Learning for Safety Critical Applications
GBHT: Gradient Boosting Histogram Transform for Density Estimation
Generalised Lipschitz Regularisation Equals Distributional Robustness
Generalizable Episodic Memory for Deep Reinforcement Learning
Generalization Bounds in the Presence of Outliers: a Median-of-Means Study
Generalization Error Bound for Hyperbolic Ordinal Embedding
Generalization Guarantees for Neural Architecture Search with Train-Validation Split
Generalized Doubly Reparameterized Gradient Estimators
Generating images with sparse representations
Generative Adversarial Networks for Markovian Temporal Dynamics: Stochastic Continuous Data Generation
Generative Adversarial Transformers
Generative Causal Explanations for Graph Neural Networks
Generative Particle Variational Inference via Estimation of Functional Gradients
Generative Video Transformer: Can Objects be the Words?
GeomCA: Geometric Evaluation of Data Representations
Geometric convergence of elliptical slice sampling
Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances
Global Convergence of Policy Gradient for Linear-Quadratic Mean-Field Control/Game in Continuous Time
Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processes
Globally-Robust Neural Networks
Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs
Global Prosody Style Transfer Without Text Transcriptions

« prev Page 9/24 next »