Doubly Robust Data-Driven Distributionally Robust Optimization

Abstract

Data-driven Distributionally Robust Optimization (DD-DRO) via optimal transport has been shown to encompass a wide range of popular machine learning algorithms. The distributional uncertainty size is often shown to correspond to the regularization parameter. The type of regularization (e.g. the norm used to regularize) corresponds to the shape of the distributional uncertainty. We propose a data-driven robust optimization methodology to inform the transportation cost underlying the definition of the distributional uncertainty. We show empirically that this additional layer of robustification, which produces a method we called doubly robust data-driven distributionally robust optimization (DD-R-DRO), allows to enhance the generalization properties of regularized estimators while reducing testing error relative to state-of-the-art classifiers in a wide range of data sets.

arXiv admin note: substantial text overlap with arXiv:1705.07152

References in corpus (6)

• Square-Root Lasso: Pivotal Recovery of Sparse Signals via Conic Programming
• A Survey on Metric Learning for Feature Vectors and Structured Data
• Robustness and Regularization of Support Vector Machines
• Robust Wasserstein Profile Inference and Applications to Machine Learning
• Distributionally Robust Logistic Regression
• Robust Metric Learning by Smooth Optimization

Cited by in corpus (5)

• Distributionally Robust Optimization: A Review
• Data-Driven Distributionally Robust Optimal Power Flow for Distribution Systems
• Sample Out-Of-Sample Inference Based on Wasserstein Distance
• Partition-based Distributionally Robust Optimization via Optimal Transport with Order Cone Constraints
• Are Adversarial Examples Created Equal? A Learnable Weighted Minimax Risk for Robustness under Non-uniform Attacks