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
A statistical perspective on distillation
A Structured Observation Distribution for Generative Biological Sequence Prediction and Forecasting
A Survey of Deep Learning Based Object Detection
Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections
Asymmetric Loss Functions for Learning with Noisy Labels
Asymptotic Normality and Confidence Intervals for Prediction Risk of the Min-Norm Least Squares Estimator
Asymptotics of Ridge Regression in Convolutional Models
Asynchronous Decentralized Optimization With Implicit Stochastic Variance Reduction
Asynchronous Distributed Learning : Adapting to Gradient Delays without Prior Knowledge
A Tale of Two Efficient and Informative Negative Sampling Distributions
A theory of high dimensional regression with arbitrary correlations between input features and target functions: sample complexity, multiple descent curves and a hierarchy of phase transitions
A Theory of Label Propagation for Subpopulation Shift
Attention is not all you need: pure attention loses rank doubly exponentially with depth
Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment
A Unified Generative Adversarial Network Training via Self-Labeling and Self-Attention
A Unified Lottery Ticket Hypothesis for Graph Neural Networks
AutoAttend: Automated Attention Representation Search
Autoencoder Image Interpolation by Shaping the Latent Space
Autoencoding Under Normalization Constraints
Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators
Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting
AutoSampling: Search for Effective Data Sampling Schedules
A Value-Function-based Interior-point Method for Non-convex Bi-level Optimization
Average-Reward Off-Policy Policy Evaluation with Function Approximation
A Wasserstein Minimax Framework for Mixed Linear Regression
A Zeroth-Order Block Coordinate Descent Algorithm for Huge-Scale Black-Box Optimization
Backdoor Scanning for Deep Neural Networks through K-Arm Optimization
Backpropagated Neighborhood Aggregation for Accurate Training of Spiking Neural Networks
BANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale Pretraining
Barlow Twins: Self-Supervised Learning via Redundancy Reduction
BASE Layers: Simplifying Training of Large, Sparse Models
BASGD: Buffered Asynchronous SGD for Byzantine Learning
BasisDeVAE: Interpretable Simultaneous Dimensionality Reduction and Feature-Level Clustering with Derivative-Based Variational Autoencoders
Batch Value-function Approximation with Only Realizability
Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information
Bayesian Attention Belief Networks
Bayesian Deep Learning via Subnetwork Inference
Bayesian Optimistic Optimisation with Exponentially Decaying Regret
Bayesian Optimization over Hybrid Spaces
Bayesian Quadrature on Riemannian Data Manifolds
Bayesian Structural Adaptation for Continual Learning
Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement
Besov Function Approximation and Binary Classification on Low-Dimensional Manifolds Using Convolutional Residual Networks
Best Arm Identification in Graphical Bilinear Bandits
Best Model Identification: A Rested Bandit Formulation
Better Training using Weight-Constrained Stochastic Dynamics
Beyond log2(T) regret for decentralized bandits in matching markets
Beyond log(T) regret for decentralized bandits in matching markets
Beyond the Pareto Efficient Frontier: Constraint Active Search for Multiobjective Experimental Design
Beyond Variance Reduction: Understanding the True Impact of Baselines on Policy Optimization

« prev Page 3/24 next »