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
Projection-free Distributed Online Convex Optimization with $O(\sqrt{T})$ Communication Complexity
Projective Preferential Bayesian Optimization
Proper Network Interpretability Helps Adversarial Robustness in Classification
Provable guarantees for decision tree induction: the agnostic setting
Provable Representation Learning for Imitation Learning via Bi-level Optimization
Provable Self-Play Algorithms for Competitive Reinforcement Learning
Provable Smoothness Guarantees for Black-Box Variational Inference
Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function Approximation
Provably Efficient Exploration in Policy Optimization
Provably Efficient Model-based Policy Adaptation
Proving the Lottery Ticket Hypothesis: Pruning is All You Need
Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup
Quadratically Regularized Subgradient Methods for Weakly Convex Optimization with Weakly Convex Constraints
Quantized Decentralized Stochastic Learning over Directed Graphs
Quantum Boosting
Quantum Expectation-Maximization for Gaussian mixture models
Q-value Path Decomposition for Deep Multiagent Reinforcement Learning
R2-B2: Recursive Reasoning-Based Bayesian Optimization for No-Regret Learning in Games
Random extrapolation for primal-dual coordinate descent
Random Hypervolume Scalarizations for Provable Multi-Objective Black Box Optimization
Randomization matters How to defend against strong adversarial attacks
Randomized Block-Diagonal Preconditioning for Parallel Learning
Randomized Smoothing of All Shapes and Sizes
Randomly Projected Additive Gaussian Processes for Regression
Random Matrix Theory Proves that Deep Learning Representations of GAN-data Behave as Gaussian Mixtures
Rank Aggregation from Pairwise Comparisons in the Presence of Adversarial Corruptions
Rate-distortion optimization guided autoencoder for isometric embedding in Euclidean latent space
Ready Policy One: World Building Through Active Learning
Real-Time Optimisation for Online Learning in Auctions
Recht-Re Noncommutative Arithmetic-Geometric Mean Conjecture is False
Recovery of Sparse Signals from a Mixture of Linear Samples
Recurrent Hierarchical Topic-Guided RNN for Language Generation
Reducing Sampling Error in Batch Temporal Difference Learning
Refined bounds for algorithm configuration: The knife-edge of dual class approximability
Regularized Optimal Transport is Ground Cost Adversarial
Reinforcement Learning for Integer Programming: Learning to Cut
Reinforcement Learning for Molecular Design Guided by Quantum Mechanics
Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimism
Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound
Relaxing Bijectivity Constraints with Continuously Indexed Normalising Flows
Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks
Reliable Fidelity and Diversity Metrics for Generative Models
Representation Learning via Adversarially-Contrastive Optimal Transport
Representations for Stable Off-Policy Reinforcement Learning
Representing Unordered Data Using Complex-Weighted Multiset Automata
Reserve Pricing in Repeated Second-Price Auctions with Strategic Bidders
Responsive Safety in Reinforcement Learning by PID Lagrangian Methods
Restarted Bayesian Online Change-point Detector achieves Optimal Detection Delay
Rethinking Bias-Variance Trade-off for Generalization of Neural Networks
Retrieval Augmented Language Model Pre-Training

« prev Page 17/22 next »