Saved in:
Bibliographic Details
Main Authors: Geiersbach, Caroline, Milz, Johannes
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.06982
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918380365152256
author Geiersbach, Caroline
Milz, Johannes
author_facet Geiersbach, Caroline
Milz, Johannes
contents This paper is concerned with a class of stochastic optimization problems defined on a Banach space with almost sure conic-type constraints. For this class of problems, we investigate the consistency of optimal values and solutions corresponding to sample average approximation. Consistency is also shown in the case where a Moreau--Yosida-type regularization of the constraint is used. Additionally, the consistency of Karush--Kuhn--Tucker conditions is shown under mild conditions. This work provides theoretical justification for the numerical computation of solutions frequently used in the literature. Several applications are explored showing the flexibility of the framework. We cover nonparametric regression over Sobolev balls, operator learning, optimal transport, optimization with dynamical systems under uncertainty, and optimization with partial differential equations under uncertainty.
format Preprint
id arxiv_https___arxiv_org_abs_2507_06982
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sample-Based Consistency in Infinite-Dimensional Conic-Constrained Stochastic Optimization
Geiersbach, Caroline
Milz, Johannes
Optimization and Control
This paper is concerned with a class of stochastic optimization problems defined on a Banach space with almost sure conic-type constraints. For this class of problems, we investigate the consistency of optimal values and solutions corresponding to sample average approximation. Consistency is also shown in the case where a Moreau--Yosida-type regularization of the constraint is used. Additionally, the consistency of Karush--Kuhn--Tucker conditions is shown under mild conditions. This work provides theoretical justification for the numerical computation of solutions frequently used in the literature. Several applications are explored showing the flexibility of the framework. We cover nonparametric regression over Sobolev balls, operator learning, optimal transport, optimization with dynamical systems under uncertainty, and optimization with partial differential equations under uncertainty.
title Sample-Based Consistency in Infinite-Dimensional Conic-Constrained Stochastic Optimization
topic Optimization and Control
url https://arxiv.org/abs/2507.06982