EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

A deep learning approach to multi-marginal optimal transport via Hilbert space embeddings of probability measures

Yumiharu Nakano, Takafumi Saito

Statistics and Computing · 2026-06 · 36 (3)

DOI: 10.1007/s11222-026-10871-3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Statistics and Computing, online erschienen am 07.04.2026. Verfasst von Yumiharu Nakano und 1 weiteren Autor:innen. Die Arbeit nennt 17 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Japan Society for the Promotion of Science.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We propose a numerical method for solving the multi-marginal Monge problem, which extends the classical Monge formulation to settings involving multiple target distributions. Our approach is based on the Hilbert space embedding of probability measures and employs a penalization technique using the maximum mean discrepancy to enforce marginal constraints. The method is designed to be computationally efficient, enabling GPU-based implementation suitable for large-scale problems. We confirm the effectiveness of the proposed method through numerical experiments using synthetic data.

Förderung

  • Japan Society for the Promotion of Science

Zitieren

APA

Nakano, Y., & Saito, T. (2026). A deep learning approach to multi-marginal optimal transport via Hilbert space embeddings of probability measures. Statistics and Computing, 36(3). https://doi.org/10.1007/s11222-026-10871-3

Vancouver

Nakano Y, Saito T. A deep learning approach to multi-marginal optimal transport via Hilbert space embeddings of probability measures. Statistics and Computing. 2026;36(3). doi:10.1007/s11222-026-10871-3

BibTeX
@article{Nakano2026,
  author = {Nakano, Yumiharu and Saito, Takafumi},
  title = {A deep learning approach to multi-marginal optimal transport via Hilbert space embeddings of probability measures},
  journal = {Statistics and Computing},
  year = {2026},
  volume = {36},
  number = {3},
  doi = {10.1007/s11222-026-10871-3}
}
Kostenlos starten →