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
Bias-Free Scalable Gaussian Processes via Randomized Truncations
Bias-Robust Bayesian Optimization via Dueling Bandits
Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning
Biclustering analysis of gene expression data using multi-objective evolutionary algorithms
Bilevel Optimization: Convergence Analysis and Enhanced Design
Bilinear Classes: A Structural Framework for Provable Generalization in RL
Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification
Black-box density function estimation using recursive partitioning
Blind Pareto Fairness and Subgroup Robustness
Boosting for Online Convex Optimization
Boosting the Intelligibility of Waveform Speech Enhancement Networks through Self-supervised Representations
Boosting the Throughput and Accelerator Utilization of Specialized CNN Inference Beyond Increasing Batch Size
Bootstrapping Fitted Q-Evaluation for Off-Policy Inference
BORE: Bayesian Optimization by Density-Ratio Estimation
Breaking the Deadly Triad with a Target Network
Breaking the Limits of Message Passing Graph Neural Networks
Break-It-Fix-It: Unsupervised Learning for Program Repair
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation
Budgeted Heterogeneous Treatment Effect Estimation
Byzantine-Resilient High-Dimensional SGD with Local Iterations on Heterogeneous Data
Calibrate Before Use: Improving Few-shot Performance of Language Models
Can Subnetwork Structure Be the Key to Out-of-Distribution Generalization?
CARTL: Cooperative Adversarially-Robust Transfer Learning
Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization
CATE: Computation-aware Neural Architecture Encoding with Transformers
Catformer: Designing Stable Transformers via Sensitivity Analysis
Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning
Causality-aware counterfactual confounding adjustment as an alternative to linear residualization in anticausal prediction tasks based on linear learners
ChaCha for Online AutoML
Characterizing Fairness Over the Set of Good Models Under Selective Labels
Characterizing Structural Regularities of Labeled Data in Overparameterized Models
Characterizing the Gap Between Actor-Critic and Policy Gradient
Chebyshev Polynomial Codes: Task Entanglement-based Coding for Distributed Matrix Multiplication
CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection
Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels
Classification with Rejection Based on Cost-sensitive Classification
Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed
CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients
Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels
Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learning
Coach-Player Multi-agent Reinforcement Learning for Dynamic Team Composition
Coded-InvNet for Resilient Prediction Serving Systems
Collaborative Bayesian Optimization with Fair Regret
Colour-emotion association study on abstract art painting
Combinatorial Blocking Bandits with Stochastic Delays
Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning
CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints
Communication-Efficient Distributed Optimization with Quantized Preconditioners
Communication-Efficient Distributed SVD via Local Power Iterations
Commutative Lie Group VAE for Disentanglement Learning

« prev Page 4/24 next »