A Wasserstein-type metric for generic mixture models, including location-scatter and group invariant measures - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Preprints, Working Papers, ... Year : 2023

A Wasserstein-type metric for generic mixture models, including location-scatter and group invariant measures

Abstract

In this article, we study Wasserstein-type metrics and corresponding barycenters for mixtures of a chosen subset of probability measures called atoms hereafter. In particular, this works extends what was proposed by Delon and Desolneux [10] for mixtures of gaussian measures to other mixtures. We first prove in a general setting that for a set of atoms equipped with a metric that defines a geodesic space, the set of mixtures based on this set of atoms is also geodesic space for the defined modified Wasserstein metric. We then focus on two particular cases of sets of atoms: (i) the set of location-scatter atoms and (ii) the set of measures that are invariant with respect to some symmetry group. Both cases are particularly relevant for various applications among which electronic structure calculations. Along the way, we also prove some sparsity and symmetry properties of optimal transport plans between measures that are invariant under some well-chosen symmetries.
Fichier principal
Vignette du fichier
main.pdf (1.51 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03946436 , version 1 (19-01-2023)

Identifiers

  • HAL Id : hal-03946436 , version 1

Cite

Geneviève Dusson, Virginie Ehrlacher, Nathalie Nouaime. A Wasserstein-type metric for generic mixture models, including location-scatter and group invariant measures. 2023. ⟨hal-03946436⟩
113 View
73 Download

Share

Gmail Mastodon Facebook X LinkedIn More