Penalization of Barycenters in the Wasserstein Space
| hal.structure.identifier | Institut de Mathématiques de Bordeaux [IMB] | |
| dc.contributor.author | BIGOT, Jérémie | |
| hal.structure.identifier | Institut de Mathématiques de Bordeaux [IMB] | |
| dc.contributor.author | CAZELLES, Elsa | |
| hal.structure.identifier | Institut de Mathématiques de Bordeaux [IMB] | |
| dc.contributor.author | PAPADAKIS, Nicolas | |
| dc.date.accessioned | 2024-04-04T03:09:44Z | |
| dc.date.available | 2024-04-04T03:09:44Z | |
| dc.date.issued | 2019 | |
| dc.identifier.issn | 0036-1410 | |
| dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/193631 | |
| dc.description.abstractEn | A regularization of Wasserstein barycenters for random measures supported on $R^$d is introduced via convex penalization. The existence and uniqueness of such barycenters is proved for a large class of penalization functions. A stability result of regularized barycenters in terms of Bregman distance associated to the penalization term is also given. This allows to compare the case of data made of n probability measures with the more realistic setting where we have only access to a dataset of random variables sampled from unknown distributions. We also analyze the convergence of the regularized empirical barycenter of a set of n iid random probability measures towards its population counterpart, and we discuss its rate of convergence. This approach is shown to be appropriate for the statistical analysis of discrete or absolutely continuous random measures. In this setting, we propose efficient algorithms for the computation of penalized Wasserstein barycenters. This approach is finally illustrated with simulated and real data sets. | |
| dc.description.sponsorship | Generalized Optimal Transport Models for Image processing - ANR-16-CE33-0010 | |
| dc.language.iso | en | |
| dc.publisher | Society for Industrial and Applied Mathematics | |
| dc.title.en | Penalization of Barycenters in the Wasserstein Space | |
| dc.type | Article de revue | |
| dc.subject.hal | Informatique [cs]/Traitement du signal et de l'image | |
| dc.subject.hal | Statistiques [stat]/Théorie [stat.TH] | |
| bordeaux.journal | SIAM Journal on Mathematical Analysis | |
| bordeaux.page | 2261–2285 | |
| bordeaux.volume | 51 | |
| bordeaux.hal.laboratories | Institut de Mathématiques de Bordeaux (IMB) - UMR 5251 | * |
| bordeaux.issue | 3 | |
| bordeaux.institution | Université de Bordeaux | |
| bordeaux.institution | Bordeaux INP | |
| bordeaux.institution | CNRS | |
| bordeaux.peerReviewed | oui | |
| hal.identifier | hal-01564007 | |
| hal.version | 1 | |
| hal.popular | non | |
| hal.audience | Internationale | |
| hal.origin.link | https://hal.archives-ouvertes.fr//hal-01564007v1 | |
| bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=SIAM%20Journal%20on%20Mathematical%20Analysis&rft.date=2019&rft.volume=51&rft.issue=3&rft.spage=2261%E2%80%932285&rft.epage=2261%E2%80%932285&rft.eissn=0036-1410&rft.issn=0036-1410&rft.au=BIGOT,%20J%C3%A9r%C3%A9mie&CAZELLES,%20Elsa&PAPADAKIS,%20Nicolas&rft.genre=article |
Fichier(s) constituant ce document
| Fichiers | Taille | Format | Vue |
|---|---|---|---|
|
Il n'y a pas de fichiers associés à ce document. |
|||