On the sample complexity of entropic optimal transport
The Annals of Statistics · 01.02.2025 · 53 (1) · 61-90
DOI: 10.1214/24-aos2455 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Annals of Statistics, erschienen am 01.02.2025. Verfasst von Philippe Rigollet und 1 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 89 Literaturangaben.
Abstract (Originalsprache)
We study the sample complexity of entropic optimal transport in high dimensions using computationally efficient plug-in estimators. We significantly advance the state of the art by establishing dimension-free, parametric rates for estimating various quantities of interest, including the entropic regression function, which is a natural analog to the optimal transport map. As an application, we propose a practical model for transfer learning based on entropic optimal transport and establish parametric rates of convergence for nonparametric regression and classification.
Zitieren
APA
Rigollet, P., & Stromme, A. J. (2025). On the sample complexity of entropic optimal transport. The Annals of Statistics, 53(1), 61-90. https://doi.org/10.1214/24-aos2455
Vancouver
Rigollet P, Stromme AJ. On the sample complexity of entropic optimal transport. The Annals of Statistics. 2025;53(1):61-90. doi:10.1214/24-aos2455
BibTeX
@article{Rigollet2025,
author = {Rigollet, Philippe and Stromme, Austin J.},
title = {On the sample complexity of entropic optimal transport},
journal = {The Annals of Statistics},
year = {2025},
volume = {53},
number = {1},
pages = {61--90},
doi = {10.1214/24-aos2455}
}
EUVIMED