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
Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization
Compositional Video Synthesis with Action Graphs
Compressed Maximum Likelihood
Concentric mixtures of Mallows models for top-k rankings: sampling and identifiability
Conditional Distributional Treatment Effect with Kernel Conditional Mean Embeddings and U-Statistic Regression
Conditional Temporal Neural Processes with Covariance Loss
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
Confidence-Budget Matching for Sequential Budgeted Learning
Confidence Scores Make Instance-dependent Label-noise Learning Possible
Conformal prediction interval for dynamic time-series
Conjugate Energy-Based Models
Connecting Interpretability and Robustness in Decision Trees through Separation
Connecting Optimal Ex-Ante Collusion in Teams to Extensive-Form Correlation: Faster Algorithms and Positive Complexity Results
Connecting Sphere Manifolds Hierarchically for Regularization
Consensus Control for Decentralized Deep Learning
Conservative Objective Models for Effective Offline Model-Based Optimization
Consistent Nonparametric Methods for Network Assisted Covariate Estimation
Consistent regression when oblivious outliers overwhelm
Context-Aware Online Collective Inference for Templated Graphical Models
Continual Learning in the Teacher-Student Setup: Impact of Task Similarity
Continuous Coordination As a Realistic Scenario for Lifelong Learning
Continuous-time Model-based Reinforcement Learning
Contrastive Learning Inverts the Data Generating Process
Controlling Graph Dynamics with Reinforcement Learning and Graph Neural Networks
Convex Regularization in Monte-Carlo Tree Search
ConvexVST: A Convex Optimization Approach to Variance-stabilizing Transformation
ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases
Cooperative Exploration for Multi-Agent Deep Reinforcement Learning
Correcting Exposure Bias for Link Recommendation
Correlation Clustering in Constant Many Parallel Rounds
Counterfactual Credit Assignment in Model-Free Reinforcement Learning
CountSketches, Feature Hashing and the Median of Three
Credit Default Risk Prediction of Lenders with Resampling Methods
CRFL: Certifiably Robust Federated Learning against Backdoor Attacks
Cross-domain Imitation from Observations
Cross-Gradient Aggregation for Decentralized Learning from Non-IID Data
Cross-model Back-translated Distillation for Unsupervised Machine Translation
Crowdsourcing via Annotator Co-occurrence Imputation and Provable Symmetric Nonnegative Matrix Factorization
CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee
Crystallization Learning with the Delaunay Triangulation
Cumulants of Hawkes Processes are Robust to Observation Noise
CURI: A Benchmark for Productive Concept Learning Under Uncertainty
Cyclically Equivariant Neural Decoders for Cyclic Codes
DAGs with No Curl: An Efficient DAG Structure Learning Approach
DANCE: Enhancing saliency maps using decoys
Dash: Semi-Supervised Learning with Dynamic Thresholding
Data augmentation for deep learning based accelerated MRI reconstruction with limited data
Data Augmentation for Meta-Learning
Data-driven Prediction of General Hamiltonian Dynamics via Learning Exactly-Symplectic Maps
Data-efficient Hindsight Off-policy Option Learning

« prev Page 5/24 next »