Reconstructing discrete measures from projections. Consequences on the empirical Sliced Wasserstein Distance - CNRS - Centre national de la recherche scientifique
Pré-Publication, Document De Travail Année : 2023

Reconstructing discrete measures from projections. Consequences on the empirical Sliced Wasserstein Distance

Résumé

This paper deals with the reconstruction of a discrete measure γ Z on R d from the knowledge of its pushforward measures P i #γ Z by linear applications P i : R d → R di (for instance projections onto subspaces). The measure γ Z being fixed, assuming that the rows of the matrices P i are independent realizations of laws which do not give mass to hyperplanes, we show that if i d i > d, this reconstruction problem has almost certainly a unique solution. This holds for any number of points in γ Z. A direct consequence of this result is an almost-sure separability property on the empirical Sliced Wasserstein distance.
Fichier principal
Vignette du fichier
main_arxiv.pdf (466.64 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04232769 , version 1 (09-10-2023)
hal-04232769 , version 2 (18-03-2024)

Identifiants

Citer

Eloi Tanguy, Rémi Flamary, Julie Delon. Reconstructing discrete measures from projections. Consequences on the empirical Sliced Wasserstein Distance. 2023. ⟨hal-04232769v1⟩
61 Consultations
60 Téléchargements

Altmetric

Partager

More