Worst-Case Risk Quantification under Distributional Ambiguity using Kernel Mean Embedding in Moment Problem
Optimization and Control
2020-09-08 v2 Machine Learning
Systems and Control
Systems and Control
Abstract
In order to anticipate rare and impactful events, we propose to quantify the worst-case risk under distributional ambiguity using a recent development in kernel methods -- the kernel mean embedding. Specifically, we formulate the generalized moment problem whose ambiguity set (i.e., the moment constraint) is described by constraints in the associated reproducing kernel Hilbert space in a nonparametric manner. We then present the tractable approximation and its theoretical justification. As a concrete application, we numerically test the proposed method in characterizing the worst-case constraint violation probability in the context of a constrained stochastic control system.
Cite
@article{arxiv.2004.00166,
title = {Worst-Case Risk Quantification under Distributional Ambiguity using Kernel Mean Embedding in Moment Problem},
author = {Jia-Jie Zhu and Wittawat Jitkrittum and Moritz Diehl and Bernhard Schölkopf},
journal= {arXiv preprint arXiv:2004.00166},
year = {2020}
}