Flow-Based Distributionally Robust Optimization
IEEE Journal on Selected Areas in Information Theory · 2024 · 5 · 62-77
DOI: 10.1109/jsait.2024.3370699 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Journal on Selected Areas in Information Theory, 2024. Verfasst von Chen Xu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: NSF CAREER, Coca-Cola Foundation, NSF.
Abstract (Originalsprache)
We present a computationally efficient framework, called FlowDRO, for solving flow-based distributionally robust optimization (DRO) problems with Wasserstein uncertainty sets while aiming to find continuous worst-case distribution (also called the Least Favorable Distribution, LFD) and sample from it. The requirement for LFD to be continuous is so that the algorithm can be scalable to problems with larger sample sizes and achieve better generalization capability for the induced robust algorithms. To tackle the computationally challenging infinitely dimensional optimization problem, we leverage flow-based models and continuous-time invertible transport maps between the data distribution and the target distribution and develop a Wasserstein proximal gradient flow type algorithm. In theory, we establish the equivalence of the solution by optimal transport map to the original formulation, as well as the dual form of the problem through Wasserstein calculus and Brenier theorem. In practice, we parameterize the transport maps by a sequence of neural networks progressively trained in blocks by gradient descent. We demonstrate its usage in adversarial learning, distributionally robust hypothesis testing, and a new mechanism for data-driven distribution perturbation differential privacy, where the proposed method gives strong empirical performance on high-dimensional real data.
Förderung
- NSF CAREER
- Coca-Cola Foundation
- NSF
- Simons Foundation
Zitieren
APA
Xu, C., Lee, J., Cheng, X., & Xie, Y. (2024). Flow-Based Distributionally Robust Optimization. IEEE Journal on Selected Areas in Information Theory, 5, 62-77. https://doi.org/10.1109/jsait.2024.3370699
Vancouver
Xu C, Lee J, Cheng X, Xie Y. Flow-Based Distributionally Robust Optimization. IEEE Journal on Selected Areas in Information Theory. 2024;5:62-77. doi:10.1109/jsait.2024.3370699
BibTeX
@article{Xu2024,
author = {Xu, Chen and Lee, Jonghyeok and Cheng, Xiuyuan and Xie, Yao},
title = {Flow-Based Distributionally Robust Optimization},
journal = {IEEE Journal on Selected Areas in Information Theory},
year = {2024},
volume = {5},
pages = {62--77},
doi = {10.1109/jsait.2024.3370699}
}
EUVIMED