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
Streaming and Distributed Algorithms for Robust Column Subset Selection
Streaming Bayesian Deep Tensor Factorization
Street2Sat: A Machine Learning Pipeline for Generating Ground-truth Geo-referenced Labeled Datasets from Street-Level Images
STRODE: Stochastic Boundary Ordinary Differential Equation
Structured Convolutional Kernel Networks for Airline Crew Scheduling
Structured World Belief for Reinforcement Learning in POMDP
Submodular Maximization subject to a Knapsack Constraint: Combinatorial Algorithms with Near-optimal Adaptive Complexity
SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning
Supervised Tree-Wasserstein Distance
SUPRDAD: A Robust Feature Extractor Better Recognizes Low-Prevalent Retinal Diseases
Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approach
Synthesizer: Rethinking Self-Attention for Transformer Models
Systematic Analysis of Cluster Similarity Indices: How to Validate Validation Measures
Targeted Data Acquisition for Evolving Negotiation Agents
Task-Optimal Exploration in Linear Dynamical Systems
Taylor Expansion of Discount Factors
TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL
Temporal Difference Learning as Gradient Splitting
Temporally Correlated Task Scheduling for Sequence Learning
Temporal Predictive Coding For Model-Based Planning In Latent Space
TempoRL: Learning When to Act
Tensor Programs IIb: Architectural Universality Of Neural Tangent Kernel Training Dynamics
Tensor Programs IV: Feature Learning in Infinite-Width Neural Networks
TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models
Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning
Testing DNN-based Autonomous Driving Systems under Critical Environmental Conditions
Testing Group Fairness via Optimal Transport Projections
TFix: Learning to Fix Coding Errors with a Text-to-Text Transformer
The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation
The Earth Mover's Pinball Loss: Quantiles for Histogram-Valued Regression
The Emergence of Individuality
The Heavy-Tail Phenomenon in SGD
The Hintons in your Neural Network: a Quantum Field Theory View of Deep Learning
The Impact of Record Linkage on Learning from Feature Partitioned Data
The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks
The Limits of Min-Max Optimization Algorithms: Convergence to Spurious Non-Critical Sets
The Lipschitz Constant of Self-Attention
The Logical Options Framework
Theory of Spectral Method for Union of Subspaces-Based Random Geometry Graph
The Power of Adaptivity for Stochastic Submodular Cover
The Power of Log-Sum-Exp: Sequential Density Ratio Matrix Estimation for Speed-Accuracy Optimization
The Symmetry between Arms and Knapsacks: A Primal-Dual Approach for Bandits with Knapsacks
Think Global and Act Local: Bayesian Optimisation over High-Dimensional Categorical and Mixed Search Spaces
Thinking Like Transformers
Three Operator Splitting with a Nonconvex Loss Function
Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks
Tightening the Dependence on Horizon in the Sample Complexity of Q-Learning
Tighter Bounds on the Log Marginal Likelihood of Gaussian Process Regression Using Conjugate Gradients
Tilting the playing field: Dynamical loss functions for machine learning
To be Robust or to be Fair: Towards Fairness in Adversarial Training

« prev Page 22/24 next »