EUVIMEDEUVIMED entdecken
Crossref

Randomized Wasserstein Barycenter Computation: Resampling with Statistical Guarantees

Florian Heinemann, Axel Munk, Yoav Zemel

SIAM Journal on Mathematics of Data Science · 2022-03 · 4 (1) · 229-259

DOI: 10.1137/20m1385263 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SIAM Journal on Mathematics of Data Science, online erschienen am 28.02.2022. Verfasst von Florian Heinemann und 2 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 73 Literaturangaben. Gefördert von: Swiss National Science Foundation, Deutsche Forschungsgemeinschaft, Engineering and Physical Sciences Research Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We propose a hybrid resampling method to approximate finitely supported Wasserstein barycenters on large-scale datasets, which can be combined with any exact solver. Nonasymptotic bounds on the expected error of the objective value as well as the barycenters themselves allow one to calibrate computational cost and statistical accuracy. The rate of these upper bounds is shown to be optimal and independent of the underlying dimension, which appears only in the constants. Using a simple modification of the subgradient descent algorithm of Cuturi and Doucet, we showcase the applicability of our method on myriad simulated datasets, as well as a real-data example from cell microscopy, which are out of reach for state-of-the-art algorithms for computing Wasserstein barycenters.

Förderung

  • Swiss National Science Foundation
  • Deutsche Forschungsgemeinschaft
  • Engineering and Physical Sciences Research Council

Zitieren

APA

Heinemann, F., Munk, A., & Zemel, Y. (2022). Randomized Wasserstein Barycenter Computation: Resampling with Statistical Guarantees. SIAM Journal on Mathematics of Data Science, 4(1), 229-259. https://doi.org/10.1137/20m1385263

Vancouver

Heinemann F, Munk A, Zemel Y. Randomized Wasserstein Barycenter Computation: Resampling with Statistical Guarantees. SIAM Journal on Mathematics of Data Science. 2022;4(1):229-259. doi:10.1137/20m1385263

BibTeX
@article{Heinemann2022,
  author = {Heinemann, Florian and Munk, Axel and Zemel, Yoav},
  title = {Randomized Wasserstein Barycenter Computation: Resampling with Statistical Guarantees},
  journal = {SIAM Journal on Mathematics of Data Science},
  year = {2022},
  volume = {4},
  number = {1},
  pages = {229--259},
  doi = {10.1137/20m1385263}
}
Kostenlos starten →