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
Unitary Branching Programs: Learnability and Lower Bounds
Unsupervised Co-part Segmentation through Assembly
Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classification
Unsupervised Learning of Visual 3D Keypoints for Control
Unsupervised Part Representation by Flow Capsules
Unsupervised Representation Learning via Neural Activation Coding
Unsupervised Skill Discovery with Bottleneck Option Learning
Valid Causal Inference with (Some) Invalid Instruments
Value Alignment Verification
Value-at-Risk Optimization with Gaussian Processes
Value Iteration in Continuous Actions, States and Time
Variance Reduced Training with Stratified Sampling for Forecasting Models
Variance Reduction via Primal-Dual Accelerated Dual Averaging for Nonsmooth Convex Finite-Sums
Variational Auto-Regressive Gaussian Processes for Continual Learning
Variational Data Assimilation with a Learned Inverse Observation Operator
Variational Empowerment as Representation Learning for Goal-Conditioned Reinforcement Learning
Variational (Gradient) Estimate of the Score Function in Energy-based Latent Variable Models
Vector Quantized Models for Planning
Versatile Verification of Tree Ensembles
Video Anomaly Detection Using Dual Discriminator Based Generative Adversarial Network
ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision
Visual Analysis Of Data Sharing Research Hotspots In China Based On CiteSpace
Voice2Series: Reprogramming Acoustic Models for Time Series Classification
Wasserstein Distributional Normalization For Robust Distributional Certification of Noisy Labeled Data
Watermarking Deep Neural Networks with Greedy Residuals
Weight-covariance alignment for adversarially robust neural networks
Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks
WGAN with an Infinitely Wide Generator Has No Spurious Stationary Points
What Are Bayesian Neural Network Posteriors Really Like?
What does LIME really see in images?
What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?
What Makes for End-to-End Object Detection?
What's in the Box? Exploring the Inner Life of Neural Networks with Robust Rules
When All We Need is a Piece of the Pie: A Generic Framework for Optimizing Two-way Partial AUC
When Does Data Augmentation Help With Membership Inference Attacks?
Which transformer architecture fits my data? A vocabulary bottleneck in self-attention
Whispering to DNN: A Speech Steganographic Scheme Based on Hidden Adversarial Examples for Speech Recognition Models
Whitening and Second Order Optimization Both Make Information in the Dataset Unusable During Training, and Can Reduce or Prevent Generalization
Whitening for Self-Supervised Representation Learning
Whittle Networks: A Deep Likelihood Model for Time Series
WILDS: A Benchmark of in-the-Wild Distribution Shifts
Winograd Algorithm for AdderNet
World Model as a Graph: Learning Latent Landmarks for Planning
XOR-CD: Linearly Convergent Constrained Structure Generation
You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling
Zero-Shot Knowledge Distillation from a Decision-Based Black-Box Model
Zero-Shot Text-to-Image Generation
Zeroth-Order Non-Convex Learning via Hierarchical Dual Averaging
Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting
Zoo-Tuning: Adaptive Transfer from A Zoo of Models

« prev Page 24/24