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
On Lp-norm Robustness of Ensemble Decision Stumps and Trees
On Relativistic f-Divergences
On Second-Order Group Influence Functions for Black-Box Predictions
On Semi-parametric Inference for BART
On the consistency of top-k surrogate losses
On the Convergence of Nesterov's Accelerated Gradient Method in Stochastic Settings
On the Expressivity of Neural Networks for Deep Reinforcement Learning
On the Generalization Benefit of Noise in Stochastic Gradient Descent
On the Generalization Effects of Linear Transformations in Data Augmentation
On the Global Convergence Rates of Softmax Policy Gradient Methods
On the Global Optimality of Model-Agnostic Meta-Learning
On the (In)tractability of Computing Normalizing Constants for the Product of Determinantal Point Processes
On the Iteration Complexity of Hypergradient Computation
On the Iteration Complexity of Hypergradient Computations
On the Noisy Gradient Descent that Generalizes as SGD
On the Number of Linear Regions of Convolutional Neural Networks
On the Power of Compressed Sensing with Generative Models
On the Relation between Quality-Diversity Evaluation and Distribution-Fitting Goal in Text Generation
On the Sample Complexity of Adversarial Multi-Source PAC Learning
On the Theoretical Properties of the Network Jackknife
On the Unreasonable Effectiveness of the Greedy Algorithm: Greedy Adapts to Sharpness
On Unbalanced Optimal Transport: An Analysis of Sinkhorn Algorithm
On Validation and Planning of An Optimal Decision Rule with Application in Healthcare Studies
On Variational Learning of Controllable Representations for Text without Supervision
Operation-Aware Soft Channel Pruning using Differentiable Masks
Optimal approximation for unconstrained non-submodular minimization
Optimal Bounds between f-Divergences and Integral Probability Metrics
Optimal Continual Learning has Perfect Memory and is NP-hard
Optimal Differential Privacy Composition for Exponential Mechanisms
Optimal Estimator for Unlabeled Linear Regression
Optimally Solving Two-Agent Decentralized POMDPs Under One-Sided Information Sharing
Optimal Non-parametric Learning in Repeated Contextual Auctions with Strategic Buyer
Optimal Randomized First-Order Methods for Least-Squares Problems
Optimal Robust Learning of Discrete Distributions from Batches
Optimal Sequential Maximization: One Interview is Enough!
Optimal transport mapping via input convex neural networks
Optimistic Bounds for Multi-output Learning
Optimistic Policy Optimization with Bandit Feedback
Optimization and Analysis of the pAp@k Metric for Recommender Systems
Optimization from Structured Samples for Coverage Functions
Optimization Theory for ReLU Neural Networks Trained with Normalization Layers
Optimizer Benchmarking Needs to Account for Hyperparameter Tuning
Optimizing Black-box Metrics with Adaptive Surrogates
Optimizing Data Usage via Differentiable Rewards
Optimizing Dynamic Structures with Bayesian Generative Search
Optimizing for the Future in Non-Stationary MDPs
Optimizing Long-term Social Welfare in Recommender Systems: A Constrained Matching Approach
Option Discovery in the Absence of Rewards with Manifold Analysis
OPtions as REsponses: Grounding behavioural hierarchies in multi-agent reinforcement learning
Oracle Efficient Private Non-Convex Optimization

« prev Page 15/22 next »