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
On Variational Inference in Biclustering Models
Oops I Took A Gradient: Scalable Sampling for Discrete Distributions
Opening the Blackbox: Accelerating Neural Differential Equations by Regularizing Internal Solver Heuristics
Operationalizing Complex Causes: A Pragmatic View of Mediation
OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation
Optimal Complexity in Decentralized Training
Optimal Counterfactual Explanations in Tree Ensembles
Optimal Estimation of High Dimensional Smooth Additive Function Based on Noisy Observations
Optimal Non-Convex Exact Recovery in Stochastic Block Model via Projected Power Method
Optimal Off-Policy Evaluation from Multiple Logging Policies
Optimal regret algorithm for Pseudo-1d Bandit Convex Optimization
Optimal Streaming Algorithms for Multi-Armed Bandits
Optimal Thompson Sampling strategies for support-aware CVaR bandits
Optimal Transport Kernels for Sequential and Parallel Neural Architecture Search
Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth
Optimization Planning for 3D ConvNets
Optimizing Black-box Metrics with Iterative Example Weighting
Optimizing persistent homology based functions
Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation
Order Matters: Probabilistic Modeling of Node Sequence for Graph Generation
Outlier-Robust Optimal Transport
Out-of-Distribution Generalization via Risk Extrapolation (REx)
Outside the Echo Chamber: Optimizing the Performative Risk
Overcoming Catastrophic Forgetting by Bayesian Generative Regularization
PAC-Learning for Strategic Classification
PACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees
PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization
PAPRIKA: Private Online False Discovery Rate Control
Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics
Parallel Droplet Control in MEDA Biochips using Multi-Agent Reinforcement Learning
Parallelizing Legendre Memory Unit Training
Parallel tempering on optimized paths
Parameter-free Locally Accelerated Conditional Gradients
Parameterless Transductive Feature Re-representation for Few-Shot Learning
Parametric Graph for Unimodal Ranking Bandit
Parent-Child Separation Alarm Based on NRF24L01 and 51 Microcontroller
Pareto GAN: Extending the Representational Power of GANs to Heavy-Tailed Distributions
Partially Observed Exchangeable Modeling
Path Planning using Neural A* Search
PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration
PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training
Perceiver: General Perception with Iterative Attention
Permutation Weighting
Personalized Federated Learning using Hypernetworks
Phase Transitions, Distance Functions, and Implicit Neural Representations
Phasic Policy Gradient
PHEW : Constructing Sparse Networks that Learn Fast and Generalize Well without Training Data
PID Accelerated Value Iteration Algorithm
PipeTransformer: Automated Elastic Pipelining for Distributed Training of Large-scale Models
PixelTransformer: Sample Conditioned Signal Generation

« prev Page 17/24 next »