Principled learning method for Wasserstein distributionally robust optimization with local perturbations

Abstract

Wasserstein distributionally robust optimization (WDRO) attempts to learn a model that minimizes the local worst-case risk in the vicinity of the empirical data distribution defined by Wasserstein ball. While WDRO has received attention as a promising tool for inference since its introduction, its theoretical understanding has not been fully matured. Gao et al. (2017) proposed a minimizer based on a tractable approximation of the local worst-case risk, but without showing risk consistency. In this paper, we propose a minimizer based on a novel approximation theorem and provide the corresponding risk consistency results. Furthermore, we develop WDRO inference for locally perturbed data that include the Mixup (Zhang et al., 2017) as a special case. We show that our approximation and risk consistency results naturally extend to the cases when data are locally perturbed. Numerical experiments demonstrate robustness of the proposed method using image classification datasets. Our results show that the proposed method achieves significantly higher accuracy than baseline models on noisy datasets.

Accepted for ICML 2020

References in corpus (11)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• mixup: Beyond Empirical Risk Minimization
• Manifold Mixup: Better Representations by Interpolating Hidden States
• Certifying Some Distributional Robustness with Principled Adversarial Training
• Robust Wasserstein Profile Inference and Applications to Machine Learning
• Dropout Training as Adaptive Regularization
• Distributionally Robust Logistic Regression
• Regularization via Mass Transportation
• Does Distributionally Robust Supervised Learning Give Robust Classifiers?
• Minimax Statistical Learning with Wasserstein Distances
• Distributionally Robust Stochastic Optimization with Dependence Structure