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
Data-Free Knowledge Distillation for Heterogeneous Federated Learning
Dataset Condensation with Differentiable Siamese Augmentation
Dataset Dynamics via Gradient Flows in Probability Space
Debiasing a First-order Heuristic for Approximate Bi-level Optimization
Debiasing Model Updates for Improving Personalized Federated Training
Decentralized Riemannian Gradient Descent on the Stiefel Manifold
Decentralized Single-Timescale Actor-Critic on Zero-Sum Two-Player Stochastic Games
Deciding What to Learn: A Rate-Distortion Approach
Decision-Making Under Selective Labels: Optimal Finite-Domain Policies and Beyond
Decomposable Submodular Function Minimization via Maximum Flow
Decomposed Mutual Information Estimation for Contrastive Representation Learning
Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices
Decoupling Representation Learning from Reinforcement Learning
Decoupling Value and Policy for Generalization in Reinforcement Learning
Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design
Deep Coherent Exploration for Continuous Control
Deep Continuous Networks
Deep Generative Learning via Schrödinger Bridge
Deep Kernel Processes
Deep Latent Graph Matching
Deep Learning for Functional Data Analysis with Adaptive Basis Layers
Deeply-Debiased Off-Policy Interval Estimation
DeepOPF-NGT: A Fast Unsupervised Learning Approach for Solving AC-OPF Problems without Ground Truth
DeepReDuce: ReLU Reduction for Fast Private Inference
Deep Reinforcement Learning amidst Continual Structured Non-Stationarity
DeepWalking Backwards: From Embeddings Back to Graphs
Defense against backdoor attacks via robust covariance estimation
Delving into Deep Imbalanced Regression
Demonstration-Conditioned Reinforcement Learning for Few-Shot Imitation
Demystifying Inductive Biases for (Beta-)VAE Based Architectures
Dense for the Price of Sparse: Improved Performance of Sparsely Initialized Networks via a Subspace Offset
Density Constrained Reinforcement Learning
Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers
Detecting Rewards Deterioration in Episodic Reinforcement Learning
Detection of Metastatic Cancer on Lymph Node Sections with Deep Convolutional Neural Network
Detection of Signal in the Spiked Rectangular Models
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
DG-LMC: A Turn-key and Scalable Synchronous Distributed MCMC Algorithm via Langevin Monte Carlo within Gibbs
Dichotomous Optimistic Search to Quantify Human Perception
Differentiable Dynamic Quantization with Mixed Precision and Adaptive Resolution
Differentiable Particle Filtering via Entropy-Regularized Optimal Transport
Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision
Differentiable Spatial Planning using Transformers
Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message
Differentially Private Bayesian Inference for Generalized Linear Models
Differentially-Private Clustering of Easy Instances
Differentially Private Correlation Clustering
Differentially Private Densest Subgraph Detection
Differentially Private Quantiles
Differentially Private Query Release Through Adaptive Projection

« prev Page 6/24 next »