- This event has passed.
IEOR Seminar Series: Nam Ho-Nguyen,University of Sydney Business School
IEOR seminars occur on Mondays throughout the fall semester in room 3108 of Etcheverry Hall. Seminars feature leading-edge research from experts in industrial engineering and operations research who come from local, national, and international institutions. Seminars are open to students, faculty, and the public.
- Title: Adversarial classification via distributional robustness with Wasserstein ambiguity
- 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.
- Bio: Nam Ho-Nguyen is a Senior Lecturer in the Discipline of Business Analytics at the University of Sydney Business School. His research focuses on stochastic, robust and data-driven optimization techniques for decision-making under uncertainty.
Prior to joining the University of Sydney, he was a postdoctoral research associate at the University of Wisconsin-Madison. He graduated with a PhD degree in Operations Research from Carnegie Mellon University.