A novel notion of barycenter for probability distributions based on optimal weak mass transport - ANITI - Artificial and Natural Intelligence Toulouse Institute Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

A novel notion of barycenter for probability distributions based on optimal weak mass transport

Elsa Cazelles
Felipe Tobar
  • Fonction : Auteur
  • PersonId : 1115654
Joaquin Fontbona
  • Fonction : Auteur
  • PersonId : 839201

Résumé

We introduce weak barycenters of a family of probability distributions, based on the recently developed notion of optimal weak transport of mass by Gozlan et al. (2017) and Backhoff-Veraguas et al. (2020). We provide a theoretical analysis of this object and discuss its interpretation in the light of convex ordering between probability measures. In particular, we show that, rather than averaging the input distributions in a geometric way (as the Wasserstein barycenter based on classic optimal transport does) weak barycenters extract common geometric information shared by all the input distributions, encoded as a latent random variable that underlies all of them. We also provide an iterative algorithm to compute a weak barycenter for a finite family of input distributions, and a stochastic algorithm that computes them for arbitrary populations of laws. The latter approach is particularly well suited for the streaming setting, i.e., when distributions are observed sequentially. The notion of weak barycenter and our approaches to compute it are illustrated on synthetic examples, validated on 2D real-world data and compared to standard Wasserstein barycenters.
Fichier principal
Vignette du fichier
weakBar (1).pdf (1.17 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03160475 , version 1 (27-10-2021)
hal-03160475 , version 2 (14-01-2022)
hal-03160475 , version 3 (10-03-2023)

Identifiants

Citer

Elsa Cazelles, Felipe Tobar, Joaquin Fontbona. A novel notion of barycenter for probability distributions based on optimal weak mass transport. Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2021), NIPS: Neural Information Processing Systems Foundation, Dec 2021, Online, France. ⟨10.48550/arXiv.2102.13380⟩. ⟨hal-03160475v3⟩
183 Consultations
164 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More