First-Order Conditions for Optimization in the Wasserstein Space
SIAM Journal on Mathematics of Data Science · 31.03.2025 · 7 (1) · 274-300
DOI: 10.1137/23m156687x ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Mathematics of Data Science, online erschienen am 18.02.2025. Verfasst von Nicolas Lanzetti und 2 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 75 Literaturangaben. Gefördert von: National Center of Competence in Research Quantum Science and Technology.
Abstract (Originalsprache)
We study first-order optimality conditions for constrained optimization in the Wasserstein space, whereby one seeks to minimize a real-valued function over the space of probability measures endowed with the Wasserstein distance. Our analysis combines recent insights on the geometry and the differential structure of the Wasserstein space with more classical calculus of variations. We show that simple rationales such as “setting the derivative to zero” and “gradients are aligned at optimality” carry over to the Wasserstein space. We deploy our tools to study and solve optimization problems in the setting of distributionally robust optimization and statistical inference. The generality of our methodology allows us to naturally deal with functionals, such as mean-variance, Kullback–Leibler divergence, and Wasserstein distance, which are traditionally difficult to study in a unified framework.
Förderung
- National Center of Competence in Research Quantum Science and Technology
Zitieren
APA
Lanzetti, N., Bolognani, S., & Dörfler, F. (2025). First-Order Conditions for Optimization in the Wasserstein Space. SIAM Journal on Mathematics of Data Science, 7(1), 274-300. https://doi.org/10.1137/23m156687x
Vancouver
Lanzetti N, Bolognani S, Dörfler F. First-Order Conditions for Optimization in the Wasserstein Space. SIAM Journal on Mathematics of Data Science. 2025;7(1):274-300. doi:10.1137/23m156687x
BibTeX
@article{Lanzetti2025,
author = {Lanzetti, Nicolas and Bolognani, Saverio and Dörfler, Florian},
title = {First-Order Conditions for Optimization in the Wasserstein Space},
journal = {SIAM Journal on Mathematics of Data Science},
year = {2025},
volume = {7},
number = {1},
pages = {274--300},
doi = {10.1137/23m156687x}
}
EUVIMED