Computing Wasserstein Barycenter via operator splitting: the method of averaged marginals - Centre de Mathématiques Appliquées Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

Computing Wasserstein Barycenter via operator splitting: the method of averaged marginals

Résumé

The Wasserstein barycenter (WB) is an important tool for summarizing sets of probability measures. It finds applications in applied probability, clustering, image processing, etc. When the measures' supports are finite, computing a (balanced) WB can be done by solving a linear optimization problem whose dimensions generally exceed standard solvers' capabilities. In the more general setting where measures have different total masses, we propose a convex nonsmooth optimization formulation for the so-called unbalanced WB problem. Due to their colossal dimensions, we introduce a decomposition scheme based on the Douglas-Rachford splitting method that can be applied to both balanced and unbalanced WB problem variants. Our algorithm, which has the interesting interpretation of being built upon averaging marginals, operates a series of simple (and exact) projections that can be parallelized and even randomized, making it suitable for large-scale datasets. Numerical comparisons against state-of-the-art methods on several data sets from the literature illustrate the method's performance.
Fichier principal
Vignette du fichier
Computing_Wasserstein_Barycenters_via_operator_splitting.pdf (1.94 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04160009 , version 1 (10-08-2023)
hal-04160009 , version 2 (23-08-2023)
hal-04160009 , version 3 (06-09-2023)
hal-04160009 , version 4 (08-09-2023)
hal-04160009 , version 5 (29-07-2024)

Identifiants

Citer

D. Mimouni, P Malisani, J. Zhu, W. de Oliveira. Computing Wasserstein Barycenter via operator splitting: the method of averaged marginals. 2023. ⟨hal-04160009v5⟩
173 Consultations
26 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More