Limit theorems for entropic optimal transport maps and Sinkhorn divergence
Electronic Journal of Statistics · 01.01.2024 · 18 (1) · 980-1041
DOI: 10.1214/24-ejs2217 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronic Journal of Statistics, erschienen am 01.01.2024. Verfasst von Ziv Goldfeld und 3 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 96 Literaturangaben.
Abstract (Originalsprache)
We study limit theorems for entropic optimal transport (EOT) maps, dual potentials, and the Sinkhorn divergence. The key technical tool we use is a first and second-order Hadamard differentiability analysis of EOT potentials with respect to the marginals, which may be of independent interest. Given the differentiability results, the functional delta method is used to obtain central limit theorems for empirical EOT potentials and maps. The second-order functional delta method is leveraged to establish the limit distribution of the empirical Sinkhorn divergence under the null. Building on the latter result, we further derive the null limit distribution of the Sinkhorn independence test statistic and characterize the correct order. Since our limit theorems follow from Hadamard differentiability of the relevant maps, as a byproduct, we also obtain bootstrap consistency and asymptotic efficiency of the empirical EOT map, potentials, and Sinkhorn divergence.
Zitieren
APA
Goldfeld, Z., Kato, K., Rioux, G., & Sadhu, R. (2024). Limit theorems for entropic optimal transport maps and Sinkhorn divergence. Electronic Journal of Statistics, 18(1), 980-1041. https://doi.org/10.1214/24-ejs2217
Vancouver
Goldfeld Z, Kato K, Rioux G, Sadhu R. Limit theorems for entropic optimal transport maps and Sinkhorn divergence. Electronic Journal of Statistics. 2024;18(1):980-1041. doi:10.1214/24-ejs2217
BibTeX
@article{Goldfeld2024,
author = {Goldfeld, Ziv and Kato, Kengo and Rioux, Gabriel and Sadhu, Ritwik},
title = {Limit theorems for entropic optimal transport maps and Sinkhorn divergence},
journal = {Electronic Journal of Statistics},
year = {2024},
volume = {18},
number = {1},
pages = {980--1041},
doi = {10.1214/24-ejs2217}
}
EUVIMED