Conditional Optimal Transport on Function Spaces
SIAM/ASA Journal on Uncertainty Quantification · 31.03.2025 · 13 (1) · 304-338
DOI: 10.1137/23m1618922 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM/ASA Journal on Uncertainty Quantification, online erschienen am 19.03.2025. Verfasst von Bamdad Hosseini und 2 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 134 Literaturangaben. Gefördert von: Division of Mathematical Sciences, National Science Foundation.
Abstract (Originalsprache)
We present a systematic study of conditional triangular transport maps in function spaces from the perspective of optimal transportation and with a view towards amortized Bayesian inference. More specifically, we develop a theory of constrained optimal transport problems that describe block-triangular Monge maps that characterize conditional measures along with their Kantorovich relaxations. This work generalizes the theory of optimal triangular transport to separable infinite dimensional function spaces with general cost functions. We further tailor our results to the case of Bayesian inference problems and obtain regularity estimates on the conditioning maps from the prior to the posterior. Finally, we present numerical experiments that demonstrate the computational applicability of our theoretical results for amortized and likelihood-free inference of functional parameters.
Förderung
- Division of Mathematical Sciences
- National Science Foundation
Zitieren
APA
Hosseini, B., Hsu, A. W., & Taghvaei, A. (2025). Conditional Optimal Transport on Function Spaces. SIAM/ASA Journal on Uncertainty Quantification, 13(1), 304-338. https://doi.org/10.1137/23m1618922
Vancouver
Hosseini B, Hsu AW, Taghvaei A. Conditional Optimal Transport on Function Spaces. SIAM/ASA Journal on Uncertainty Quantification. 2025;13(1):304-338. doi:10.1137/23m1618922
BibTeX
@article{Hosseini2025,
author = {Hosseini, Bamdad and Hsu, Alexander W. and Taghvaei, Amirhossein},
title = {Conditional Optimal Transport on Function Spaces},
journal = {SIAM/ASA Journal on Uncertainty Quantification},
year = {2025},
volume = {13},
number = {1},
pages = {304--338},
doi = {10.1137/23m1618922}
}
EUVIMED