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
RNNRepair: Automatic RNN Repair via Model-based Analysis
RNN with Particle Flow for Probabilistic Spatio-temporal Forecasting
Robust Asymmetric Learning in POMDPs
Robust Density Estimation from Batches: The Best Things in Life are (Nearly) Free
Robust Inference for High-Dimensional Linear Models via Residual Randomization
Robust Learning-Augmented Caching: An Experimental Study
Robust Learning for Data Poisoning Attacks
Robust Policy Gradient against Strong Data Corruption
Robust Pure Exploration in Linear Bandits with Limited Budget
Robust Reinforcement Learning using Least Squares Policy Iteration with Provable Performance Guarantees
Robust Representation Learning via Perceptual Similarity Metrics
Robust Testing and Estimation under Manipulation Attacks
Robust Unsupervised Learning via L-statistic Minimization
RRL: Resnet as representation for Reinforcement Learning
Run-Sort-ReRun: Escaping Batch Size Limitations in Sliced Wasserstein Generative Models
Safe Reinforcement Learning Using Advantage-Based Intervention
Safe Reinforcement Learning with Linear Function Approximation
SagaNet: A Small Sample Gated Network for Pediatric Cancer Diagnosis
SAINT-ACC: Safety-Aware Intelligent Adaptive Cruise Control for Autonomous Vehicles Using Deep Reinforcement Learning
Sample Complexity of Robust Linear Classification on Separated Data
Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity
Sample-Optimal PAC Learning of Halfspaces with Malicious Noise
Sawtooth Factorial Topic Embeddings Guided Gamma Belief Network
Scalable Certified Segmentation via Randomized Smoothing
Scalable Computations of Wasserstein Barycenter via Input Convex Neural Networks
Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot
Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning
Scalable Normalizing Flows for Permutation Invariant Densities
Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More
Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition
Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing
Scaling Properties of Deep Residual Networks
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II
SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies
Segmenting Hybrid Trajectories using Latent ODEs
Selecting Data Augmentation for Simulating Interventions
Self-Damaging Contrastive Learning
Self-Improved Retrosynthetic Planning
Selfish Sparse RNN Training
Self Normalizing Flows
Self-Paced Context Evaluation for Contextual Reinforcement Learning
Self-supervised and Supervised Joint Training for Resource-rich Machine Translation
Self-supervised Graph-level Representation Learning with Local and Global Structure
Self-Tuning for Data-Efficient Deep Learning
Sequential Domain Adaptation by Synthesizing Distributionally Robust Experts
SGA: A Robust Algorithm for Partial Recovery of Tree-Structured Graphical Models with Noisy Samples
SGLB: Stochastic Gradient Langevin Boosting
SG-PALM: a Fast Physically Interpretable Tensor Graphical Model
Sharf: Shape-conditioned Radiance Fields from a Single View

« prev Page 20/24 next »