Back to Search Start Over

Kernel Distributionally Robust Optimization

Authors :
Zhu, Jia-Jie
Jitkrittum, Wittawat
Diehl, Moritz
Schölkopf, Bernhard
Source :
Proceedings of Machine Learning Research, PMLR 130:280-288, 2021
Publication Year :
2020

Abstract

We propose kernel distributionally robust optimization (Kernel DRO) using insights from the robust optimization theory and functional analysis. Our method uses reproducing kernel Hilbert spaces (RKHS) to construct a wide range of convex ambiguity sets, which can be generalized to sets based on integral probability metrics and finite-order moment bounds. This perspective unifies multiple existing robust and stochastic optimization methods. We prove a theorem that generalizes the classical duality in the mathematical problem of moments. Enabled by this theorem, we reformulate the maximization with respect to measures in DRO into the dual program that searches for RKHS functions. Using universal RKHSs, the theorem applies to a broad class of loss functions, lifting common limitations such as polynomial losses and knowledge of the Lipschitz constant. We then establish a connection between DRO and stochastic optimization with expectation constraints. Finally, we propose practical algorithms based on both batch convex solvers and stochastic functional gradient, which apply to general optimization and machine learning tasks.

Details

Database :
arXiv
Journal :
Proceedings of Machine Learning Research, PMLR 130:280-288, 2021
Publication Type :
Report
Accession number :
edsarx.2006.06981
Document Type :
Working Paper