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
Imitation by Predicting Observations
Implicit Bias of Linear RNNs
Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifold
Implicit rate-constrained optimization of non-decomposable objectives
Implicit Regularization in Tensor Factorization
Improved Algorithms for Agnostic Pool-based Active Classification
Improved Confidence Bounds for the Linear Logistic Model and Applications to Bandits
Improved Corruption Robust Algorithms for Episodic Reinforcement Learning
Improved Denoising Diffusion Probabilistic Models
Improved, Deterministic Smoothing for L_1 Certified Robustness
Improved, Deterministic Smoothing for L1 Certified Robustness
Improved OOD Generalization via Adversarial Training and Pretraing
Improved Regret Bounds of Bilinear Bandits using Action Space Analysis
Improving Breadth-Wise Backpropagation in Graph Neural Networks Helps Learning Long-Range Dependencies
Improving Generalization in Meta-learning via Task Augmentation
Improving Gradient Regularization using Complex-Valued Neural Networks
Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity
Improving Predictors via Combination Across Diverse Task Categories
Improving Ultrametrics Embeddings Through Coresets
Incentivizing Compliance with Algorithmic Instruments
In-Database Regression in Input Sparsity Time
Inferring Latent Dynamics Underlying Neural Population Activity via Neural Differential Equations
Inferring serial correlation with dynamic backgrounds
Infinite-Dimensional Optimization for Zero-Sum Games via Variational Transport
Information Obfuscation of Graph Neural Networks
Instabilities of Offline RL with Pre-Trained Neural Representation
Instance-based Label Smoothing For Better Calibrated Classification Networks
Instance-Optimal Compressed Sensing via Posterior Sampling
Instance Specific Approximations for Submodular Maximization
Integer Programming for Causal Structure Learning in the Presence of Latent Variables
Integrated Defense for Resilient Graph Matching
Interaction-Grounded Learning
Interactive Learning from Activity Description
Intermediate Layer Optimization for Inverse Problems using Deep Generative Models
Interpretable Stability Bounds for Spectral Graph Filters
Interpretable Stein Goodness-of-fit Tests on Riemannian Manifold
Interpreting and Disentangling Feature Components of Various Complexity from DNNs
Inverse Constrained Reinforcement Learning
Inverse Decision Modeling: Learning Interpretable Representations of Behavior
Ionospheric prediction of low latitude airport based on Beidou Navigation System
Isometric Gaussian Process Latent Variable Model for Dissimilarity Data
Is Pessimism Provably Efficient for Offline RL?
Is Space-Time Attention All You Need for Video Understanding?
Joining datasets via data augmentation in the label space for neural networks
Joint Online Learning and Decision-making via Dual Mirror Descent
Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks
Just Train Twice: Improving Group Robustness without Training Group Information
KB-VLP: Knowledge Based Vision and Language Pretraining
KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation
Kernel-Based Reinforcement Learning: A Finite-Time Analysis

« prev Page 11/24 next »