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
Sharing Less is More: Lifelong Learning in Deep Networks with Selective Layer Transfer
Sharper Generalization Bounds for Clustering
Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks
SiameseXML: Siamese Networks meet Extreme Classifiers with 100M Labels
SigGPDE: Scaling Sparse Gaussian Processes on Sequential Data
Signatured Deep Fictitious Play for Mean Field Games with Common Noise
SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks
Simple and Effective VAE Training with Calibrated Decoders
Simultaneous Similarity-based Self-Distillation for Deep Metric Learning
Single Pass Entrywise-Transformed Low Rank Approximation
SinIR: Efficient General Image Manipulation with Single Image Reconstruction
Sinkhorn Label Allocation: Semi-Supervised Classification via Annealed Self-Training
Size-Invariant Graph Representations for Graph Classification Extrapolations
SketchEmbedNet: Learning Novel Concepts by Imitating Drawings
Skew Orthogonal Convolutions
SKIing on Simplices: Kernel Interpolation on the Permutohedral Lattice for Scalable Gaussian Processes
Skill Discovery for Exploration and Planning using Deep Skill Graphs
Slot Machines: Discovering Winning Combinations of Random Weights in Neural Networks
SMG: A Shuffling Gradient-Based Method with Momentum
Smooth p-Wasserstein Distance: Structure, Empirical Approximation, and Statistical Applications
Soft then Hard: Rethinking the Quantization in Neural Image Compression
Solving Challenging Dexterous Manipulation Tasks With Trajectory Optimisation and Reinforcement Learning
Solving high-dimensional parabolic PDEs using the tensor train format
Solving Inverse Problems with a Flow-based Noise Model
SoundDet: Polyphonic Moving Sound Event Detection and Localization from Raw Waveform
SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation
Sparse and Imperceptible Adversarial Attack via a Homotopy Algorithm
Sparse Bayesian Learning via Stepwise Regression
SparseBERT: Rethinking the Importance Analysis in Self-attention
Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient
Sparse within Sparse Gaussian Processes using Neighbor Information
Sparsifying Networks via Subdifferential Inclusion
Sparsity-Agnostic Lasso Bandit
Spectral Normalisation for Deep Reinforcement Learning: An Optimisation Perspective
Spectral Smoothing Unveils Phase Transitions in Hierarchical Variational Autoencoders
Spectral vertex sparsifiers and pair-wise spanners over distributed graphs
SPECTRE: defending against backdoor attacks using robust statistics
SpreadsheetCoder: Formula Prediction from Semi-structured Context
Stability and Convergence of Stochastic Gradient Clipping: Beyond Lipschitz Continuity and Smoothness
Stability and Generalization of Stochastic Gradient Methods for Minimax Problems
Stabilizing Equilibrium Models by Jacobian Regularization
State Entropy Maximization with Random Encoders for Efficient Exploration
State Relevance for Off-Policy Evaluation
Statistical Estimation from Dependent Data
Stochastic Iterative Graph Matching
Stochastic Multi-Armed Bandits with Unrestricted Delay Distributions
Stochastic Sign Descent Methods: New Algorithms and Better Theory
Straight to the Gradient: Learning to Use Novel Tokens for Neural Text Generation
Strategic Classification in the Dark
Strategic Classification Made Practical

« prev Page 21/24 next »