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
Differentially Private Sliced Wasserstein Distance
Diffusion Earth Mover's Distance and Distribution Embeddings
Diffusion Source Identification on Networks with Statistical Confidence
Dimensionality Reduction for the Sum-of-Distances Metric
Directed Graph Embeddings in Pseudo-Riemannian Manifolds
Directional Bias Amplification
Directional Graph Networks
Disambiguation of Weak Supervision leading to Exponential Convergence rates
Discovering symbolic policies with deep reinforcement learning
Discrete-Valued Latent Preference Matrix Estimation with Graph Side Information
Discretization Drift in Two-Player Games
Discriminative Complementary-Label Learning with Weighted Loss
Disentangling Sampling and Labeling Bias for Learning in Large-output Spaces
Disentangling syntax and semantics in the brain with deep networks
Dissecting Supervised Constrastive Learning
Distributed Nyström Kernel Learning with Communications
Distributed Second Order Methods with Fast Rates and Compressed Communication
Distributionally Robust Optimization with Markovian Data
Distribution-Free Calibration Guarantees for Histogram Binning without Sample Splitting
Ditto: Fair and Robust Federated Learning Through Personalization
Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Exploration
Domain Generalization using Causal Matching
Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification
DORO: Distributional and Outlier Robust Optimization
Double-Win Quant: Aggressively Winning Robustness of Quantized Deep Neural Networks via Random Precision Training and Inference
Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality
DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning
Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training
DriftSurf: Stable-State / Reactive-State Learning under Concept Drift
Dropout: Explicit Forms and Capacity Control
Dual Principal Component Pursuit for Robust Subspace Learning: Theory and Algorithms for a Holistic Approach
Dueling Convex Optimization
Dynamic Balancing for Model Selection in Bandits and RL
Dynamic Game Theoretic Neural Optimizer
Dynamic Planning and Learning under Recovering Rewards
Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games
Efficient Differentiable Simulation of Articulated Bodies
Efficient Generative Modelling of Protein Structure Fragments using a Deep Markov Model
Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations
Efficient Lottery Ticket Finding: Less Data is More
Efficient Message Passing for 0-1 ILPs with Binary Decision Diagrams
EfficientNetV2: Smaller Models and Faster Training
Efficient Online Learning for Dynamic k-Clustering
Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations
Efficient Statistical Tests: A Neural Tangent Kernel Approach
Efficient Training of Robust Decision Trees Against Adversarial Examples
EfficientTTS: An Efficient and High-Quality Text-to-Speech Architecture
Elastic Graph Neural Networks
EL-Attention: Memory Efficient Lossless Attention for Generation
Elementary superexpressive activations

« prev Page 7/24 next »