Li, J., Lin, S., Blanchet, J., & Nguyen, V. A. (2022). Tikhonov Regularization is Optimal Transport Robust under Martingale Constraints. ArXiv. /abs/2210.01413
Abstract
Distributionally robust optimization (DRO) has been shown to offer a principled way to regularize learning models. In this paper, we find that Tikhonov regularization is distributionally robust in an optimal transport sense (ie if an adversary chooses distributions in a suitable optimal transport neighborhood of the empirical measure), provided that suitable martingale constraints are also imposed. Further, we introduce a relaxation of the martingale constraints which not only provide a unified viewpoint to a class of existing robust methods but also lead to new regularization tools. To realize these novel tools, provably efficient computational algorithms are proposed. As a byproduct, the strong duality theorem proved in this paper can be potentially applied to other problems of independent interest.
Authors
Jiajin Li, Sirui Lin, José Blanchet, Viet Anh Nguyen
Publication date
2022/12/6
Journal
Advances in Neural Information Processing Systems
Volume
35
Pages
17677-17689