Worst-Case Risk Quantification under Distributional Ambiguity using Kernel Mean Embedding in Moment Problem
arXiv:2004.00166
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.
References in corpus (5)
- Scikit-learn: Machine Learning in Python
- Certifying Some Distributional Robustness with Principled Adversarial Training
- Optimal Uncertainty Quantification
- On the Equivalence between Herding and Conditional Gradient Algorithms
- A New Distribution-Free Concept for Representing, Comparing, and Propagating Uncertainty in Dynamical Systems with Kernel Probabilistic Programming