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
Learning to Score Behaviors for Guided Policy Optimization
Learning to Simulate and Design for Structural Engineering
Learning to Simulate Complex Physics with Graph Networks
Learning To Stop While Learning To Predict
Learning What to Defer for Maximum Independent Sets
Learning with Bounded Instance and Label-dependent Label Noise
Learning with Feature and Distribution Evolvable Streams
Learning with Good Feature Representations in Bandits and in RL with a Generative Model
Learning with Multiple Complementary Labels
LEEP: A New Measure to Evaluate Transferability of Learned Representations
Let's Agree to Agree: Neural Networks Share Classification Order on Real Datasets
Leveraging Frequency Analysis for Deep Fake Image Recognition
Leveraging Procedural Generation to Benchmark Reinforcement Learning
Lifted Disjoint Paths with Application in Multiple Object Tracking
Likelihood-free MCMC with Amortized Approximate Ratio Estimators
Linear bandits with Stochastic Delayed Feedback
Linear Convergence of Randomized Primal-Dual Coordinate Method for Large-scale Linear Constrained Convex Programming
Linear Lower Bounds and Conditioning of Differentiable Games
Linear Mode Connectivity and the Lottery Ticket Hypothesis
(Locally) Differentially Private Combinatorial Semi-Bandits
Logarithmic Regret for Adversarial Online Control
Logarithmic Regret for Learning Linear Quadratic Regulators Efficiently
Logistic Regression for Massive Data with Rare Events
Lookahead-Bounded Q-learning
Lorentz Group Equivariant Neural Network for Particle Physics
Loss Function Search for Face Recognition
Low Bias Low Variance Gradient Estimates for Boolean Stochastic Networks
Lower Complexity Bounds for Finite-Sum Convex-Concave Minimax Optimization Problems
LowFER: Low-rank Bilinear Pooling for Link Prediction
Low-loss connection of weight vectors: distribution-based approaches
Low-Rank Bottleneck in Multi-head Attention Models
Low-Variance and Zero-Variance Baselines for Extensive-Form Games
LP-SparseMAP: Differentiable Relaxed Optimization for Sparse Structured Prediction
LTF: A Label Transformation Framework for Correcting Label Shift
Manifold Identification for Ultimately Communication-Efficient Distributed Optimization
Mapping natural-language problems to formal-language solutions using structured neural representations
Margin-aware Adversarial Domain Adaptation with Optimal Transport
Maximum-and-Concatenation Networks
Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning
Maximum Likelihood with Bias-Corrected Calibration is Hard-To-Beat at Label Shift Adaptation
Measuring Non-Expert Comprehension of Machine Learning Fairness Metrics
Median Matrix Completion: from Embarrassment to Optimality
Message Passing Least Squares: A Unified Framework for Fast and Robust Group Synchronization
Message Passing Least Squares Framework and its Application to Rotation Synchronization
MetaFun: Meta-Learning with Iterative Functional Updates
Meta-learning for Mixed Linear Regression
Meta-Learning with Shared Amortized Variational Inference
Meta-learning with Stochastic Linear Bandits
Meta Variance Transfer: Learning to Augment from the Others
Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack

« prev Page 12/22 next »