ICML 2020

1,099 papers

Top Research Directions

Research directions most represented by ICML 2020 papers.

Bypassing the Computational Bottleneck of Adversarial Training 13
Overcoming the Convexity Constraint in Modern Optimization 12
Mitigating Gradient Variance in Stochastic Optimization 11
Scaling Gaussian Processes Beyond Cubic Complexity 11
Clean Accuracy Degradation in Machine Learning Defenses 11
Mitigating Gradient Variance in Policy Optimization 10
Safe Reinforcement Learning via Constrained Markov Decision Processes 9
The Non-Linear Function Approximation Gap in Reinforcement Learning 9
Scaling Reinforcement Learning to High-Dimensional Visual Observations 8
Accelerating Neural Architecture Search Without Full Model Training 8
Navigating Non-Convex Loss Landscapes in Deep Learning 8
The Function Approximation Gap in Reinforcement Learning Theory 8
Understanding Gradient Masking in Adversarial Defenses 8
Mitigating Input Perturbation Sensitivity in Deep Networks 8
Causal Inference with Unobserved Confounding 8

Top Authors

AuthorPapers
Masashi Sugiyama11
Michael Jordan8
Dale Schuurmans7
Gang Niu7
Michal Valko7
Percy Liang7
Tommi Jaakkola7
Zhaoran Wang7
Mihaela van der Schaar6
Pieter Abbeel6
Stefano Ermon6
Yoshua Bengio6
Zhangyang Wang6
Zhuoran Yang6
Aldo Pacchiano5
Bo Han5
Chi Jin5
Heng Huang5
Jinwoo Shin5
Mehryar Mohri5

Impactful Papers

Papers from ICML 2020 that shaped research clusters.

Foundational

Influential

Papers

Title
Understanding Self-Training for Gradual Domain Adaptation
Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling
Understanding the Impact of Model Incoherence on Convergence of Incremental SGD with Random Reshuffle
Undirected Graphical Models as Approximate Posteriors
Uniform Convergence of Rank-weighted Learning
UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training
Unique Properties of Flat Minima in Deep Networks
Universal Asymptotic Optimality of Polyak Momentum
Universal Average-Case Optimality of Polyak Momentum
Universal Equivariant Multilayer Perceptrons
Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift
Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks
Unsupervised Discovery of Interpretable Directions in the GAN Latent Space
Unsupervised Speech Decomposition via Triple Information Bottleneck
Unsupervised Transfer Learning for Spatiotemporal Predictive Networks
Up or Down? Adaptive Rounding for Post-Training Quantization
Upper bounds for Model-Free Row-Sparse Principal Component Analysis
Variable Skipping for Autoregressive Range Density Estimation
Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems
Variance Reduction and Quasi-Newton for Particle-Based Variational Inference
Variance Reduction in Stochastic Particle-Optimization Sampling
Variational Autoencoders with Riemannian Brownian Motion Priors
Variational Bayesian Quantization
Variational Imitation Learning with Diverse-quality Demonstrations
Variational Inference for Sequential Data with Future Likelihood Estimates
Variational Label Enhancement
VFlow: More Expressive Generative Flows with Variational Data Augmentation
VideoOneNet: Bidirectional Convolutional Recurrent OneNet with Trainable Data Steps for Video Processing
Video Prediction via Example Guidance
Visual Grounding of Learned Physical Models
Voice Separation with an Unknown Number of Multiple Speakers
WaveFlow: A Compact Flow-based Model for Raw Audio
Weakly-Supervised Disentanglement Without Compromises
What can I do here? A Theory of Affordances in Reinforcement Learning
What Can Learned Intrinsic Rewards Capture?
What is Local Optimality in Nonconvex-Nonconcave Minimax Optimization?
When are Non-Parametric Methods Robust?
When deep denoising meets iterative phase retrieval
When Demands Evolve Larger and Noisier: Learning and Earning in a Growing Environment
When Does Self-Supervision Help Graph Convolutional Networks?
When Explanations Lie: Why Many Modified BP Attributions Fail
Which Tasks Should Be Learned Together in Multi-task Learning?
Why Are Learned Indexes So Effective?
Why bigger is not always better: on finite and infinite neural networks
Word-Level Speech Recognition With a Letter to Word Encoder
Working Memory Graphs
XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning
XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalisation
Zeno++: Robust Fully Asynchronous SGD

« prev Page 22/22