Adversarial Classification via Distributional Robustness with Wasserstein Ambiguity

DOI10.1007/S10107-022-01796-6arXiv2005.13815MaRDI QIDQ6341591

Publication date: 28 May 2020

Abstract: We study a model for adversarial classification based on distributionally robust chance constraints. We show that under Wasserstein ambiguity, the model aims to minimize the conditional value-at-risk of the distance to misclassification, and we explore links to adversarial classification models proposed earlier and to maximum-margin classifiers. We also provide a reformulation of the distributionally robust model for linear classification, and show it is equivalent to minimizing a regularized ramp loss objective. Numerical experiments show that, despite the nonconvexity of this formulation, standard descent methods appear to converge to the global minimizer for this problem. Inspired by this observation, we show that, for a certain class of distributions, the only stationary point of the regularized ramp loss minimization problem is the global minimizer.

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Nonlinear programming (90C30) Computational aspects of data analysis and big data (68T09) Robustness in mathematical programming (90C17)

This page was built for publication: Adversarial Classification via Distributional Robustness with Wasserstein Ambiguity

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6341591)