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
GLSearch: Maximum Common Subgraph Detection via Learning to Search
GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings
Goal-Conditioned Reinforcement Learning with Imagined Subgoals
GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning
Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrix
GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training
Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech
GRAND: Graph Neural Diffusion
Graph Contrastive Learning Automated
Graph Convolution for Semi-Supervised Classification: Improved Linear Separability and Out-of-Distribution Generalization
Graph Cuts Always Find a Global Optimum for Potts Models (With a Catch)
GraphDF: A Discrete Flow Model for Molecular Graph Generation
Graph Mixture Density Networks
Graph Neural Networks Inspired by Classical Iterative Algorithms
GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training
Grey-box Extraction of Natural Language Models
Grid-Functioned Neural Networks
Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning
Group Fisher Pruning for Practical Network Compression
Guarantees for Tuning the Step Size using a Learning-to-Learn Approach
Guided Exploration with Proximal Policy Optimization using a Single Demonstration
HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search
HAWQ-V3: Dyadic Neural Network Quantization
HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture
Heterogeneity for the Win: One-Shot Federated Clustering
Heterogeneous Risk Minimization
"Hey, that's not an ODE": Faster ODE Adjoints via Seminorms
Hierarchical Agglomerative Graph Clustering in Nearly-Linear Time
Hierarchical Clustering of Data Streams: Scalable Algorithms and Approximation Guarantees
Hierarchical VAEs Know What They Don't Know
High Confidence Generalization for Reinforcement Learning
High-dimensional Experimental Design and Kernel Bandits
High-Dimensional Gaussian Process Inference with Derivatives
High-Performance Large-Scale Image Recognition Without Normalization
Homomorphic Sensing: Sparsity and Noise
HoroPCA: Hyperbolic Dimensionality Reduction via Horospherical Projections
Householder Sketch for Accurate and Accelerated Least-Mean-Squares Solvers
How and Why to Use Experimental Data to Evaluate Methods for Observational Causal Inference
How could Neural Networks understand Programs?
How Do Adam and Training Strategies Help BNNs Optimization
How Does Loss Function Affect Generalization Performance of Deep Learning? Application to Human Age Estimation
How Framelets Enhance Graph Neural Networks
How Important is the Train-Validation Split in Meta-Learning?
How rotational invariance of common kernels prevents generalization in high dimensions
How to Learn when Data Reacts to Your Model: Performative Gradient Descent
HyperHyperNetwork for the Design of Antenna Arrays
Hyperparameter Selection for Imitation Learning
I-BERT: Integer-only BERT Quantization
iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients
Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection

« prev Page 10/24 next »