EUVIMEDEUVIMED entdecken
Crossref

Stability and sample complexity of divergence regularized optimal transport

Erhan Bayraktar, Stephan Eckstein, Xin Zhang

Bernoulli · 01.02.2025 · 31 (1) · 213-239

DOI: 10.3150/24-bej1725 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bernoulli, erschienen am 01.02.2025. Verfasst von Erhan Bayraktar und 2 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 63 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We study stability and sample complexity properties of divergence regularized optimal transport (DOT). First, we obtain quantitative stability results for optimizers of DOT measured in Wasserstein distance, which are applicable to a wide class of divergences and simultaneously improve known results for entropic optimal transport. Second, we study the case of sample complexity, where the DOT problem is approximated using empirical measures of the marginals. We show that divergence regularization can improve the corresponding convergence rate compared to unregularized optimal transport. To this end, we prove upper bounds which exploit both the regularity of cost function and divergence functional, as well as the intrinsic dimension of the marginals. Along the way, we establish regularity properties of dual optimizers of DOT, as well as general limit theorems for empirical measures with suitable classes of test functions.

Zitieren

APA

Bayraktar, E., Eckstein, S., & Zhang, X. (2025). Stability and sample complexity of divergence regularized optimal transport. Bernoulli, 31(1), 213-239. https://doi.org/10.3150/24-bej1725

Vancouver

Bayraktar E, Eckstein S, Zhang X. Stability and sample complexity of divergence regularized optimal transport. Bernoulli. 2025;31(1):213-239. doi:10.3150/24-bej1725

BibTeX
@article{Bayraktar2025,
  author = {Bayraktar, Erhan and Eckstein, Stephan and Zhang, Xin},
  title = {Stability and sample complexity of divergence regularized optimal transport},
  journal = {Bernoulli},
  year = {2025},
  volume = {31},
  number = {1},
  pages = {213--239},
  doi = {10.3150/24-bej1725}
}
Kostenlos starten →