Timezone: »

 
Poster
Tikhonov Regularization is Optimal Transport Robust under Martingale Constraints
Jiajin Li · Sirui Lin · Jose Blanchet · Viet Anh Nguyen

Thu Dec 01 09:00 AM -- 11:00 AM (PST) @ Hall J #726
in Poster Session 5 »

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 (i.e. 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.

Keywords: optimal transport · Distributionally Robust Optimization · Tikhonov Regularization
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Jiajin Li (Stanford University)
Sirui Lin (Stanford University)
Jose Blanchet (Stanford University)
Viet Anh Nguyen (EPFL)

More from the Same Authors