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

This paper deals with the reconstruction of a discrete measure $\gamma _Z$ on $\mathbb{R}^d$ from the knowledge of its pushforward measures $P_i\#\gamma _Z$ by linear applications $P_i: \mathbb{R}^d \rightarrow \mathbb{R}^{d_i}$ (for instance projections onto subspaces). The measure $\gamma _Z$ bein...

Full description

Saved in:
Bibliographic Details
Main Authors: Tanguy, Eloi, Flamary, Rémi, Delon, Julie
Format: Article
Language:English
Published: Académie des sciences 2024-11-01
Series:Comptes Rendus. Mathématique
Subjects:
Online Access:https://comptes-rendus.academie-sciences.fr/mathematique/articles/10.5802/crmath.601/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1825206166127378432
author Tanguy, Eloi
Flamary, Rémi
Delon, Julie
author_facet Tanguy, Eloi
Flamary, Rémi
Delon, Julie
author_sort Tanguy, Eloi
collection DOAJ
description This paper deals with the reconstruction of a discrete measure $\gamma _Z$ on $\mathbb{R}^d$ from the knowledge of its pushforward measures $P_i\#\gamma _Z$ by linear applications $P_i: \mathbb{R}^d \rightarrow \mathbb{R}^{d_i}$ (for instance projections onto subspaces). The measure $\gamma _Z$ 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 $\sum _i d_i > d$, this reconstruction problem has almost certainly a unique solution. This holds for any number of points in $\gamma _Z$. A direct consequence of this result is an almost-sure separability property on the empirical Sliced Wasserstein distance.
format Article
id doaj-art-8a3888d3c39c4c1ea93fa63c4f59e48a
institution Kabale University
issn 1778-3569
language English
publishDate 2024-11-01
publisher Académie des sciences
record_format Article
series Comptes Rendus. Mathématique
spelling doaj-art-8a3888d3c39c4c1ea93fa63c4f59e48a2025-02-07T11:23:31ZengAcadémie des sciencesComptes Rendus. Mathématique1778-35692024-11-01362G101121112910.5802/crmath.60110.5802/crmath.601Reconstructing discrete measures from projections. Consequences on the empirical Sliced Wasserstein DistanceTanguy, Eloi0Flamary, Rémi1Delon, Julie2Université Paris Cité, CNRS, MAP5, F-75006 Paris, FranceCMAP, CNRS, École Polytechnique, Institut Polytechnique de ParisUniversité Paris Cité, CNRS, MAP5, F-75006 Paris, FranceThis paper deals with the reconstruction of a discrete measure $\gamma _Z$ on $\mathbb{R}^d$ from the knowledge of its pushforward measures $P_i\#\gamma _Z$ by linear applications $P_i: \mathbb{R}^d \rightarrow \mathbb{R}^{d_i}$ (for instance projections onto subspaces). The measure $\gamma _Z$ 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 $\sum _i d_i > d$, this reconstruction problem has almost certainly a unique solution. This holds for any number of points in $\gamma _Z$. A direct consequence of this result is an almost-sure separability property on the empirical Sliced Wasserstein distance.https://comptes-rendus.academie-sciences.fr/mathematique/articles/10.5802/crmath.601/ReconstructionInverse ProblemsDiscrete Measures
spellingShingle Tanguy, Eloi
Flamary, Rémi
Delon, Julie
Reconstructing discrete measures from projections. Consequences on the empirical Sliced Wasserstein Distance
Comptes Rendus. Mathématique
Reconstruction
Inverse Problems
Discrete Measures
title Reconstructing discrete measures from projections. Consequences on the empirical Sliced Wasserstein Distance
title_full Reconstructing discrete measures from projections. Consequences on the empirical Sliced Wasserstein Distance
title_fullStr Reconstructing discrete measures from projections. Consequences on the empirical Sliced Wasserstein Distance
title_full_unstemmed Reconstructing discrete measures from projections. Consequences on the empirical Sliced Wasserstein Distance
title_short Reconstructing discrete measures from projections. Consequences on the empirical Sliced Wasserstein Distance
title_sort reconstructing discrete measures from projections consequences on the empirical sliced wasserstein distance
topic Reconstruction
Inverse Problems
Discrete Measures
url https://comptes-rendus.academie-sciences.fr/mathematique/articles/10.5802/crmath.601/
work_keys_str_mv AT tanguyeloi reconstructingdiscretemeasuresfromprojectionsconsequencesontheempiricalslicedwassersteindistance
AT flamaryremi reconstructingdiscretemeasuresfromprojectionsconsequencesontheempiricalslicedwassersteindistance
AT delonjulie reconstructingdiscretemeasuresfromprojectionsconsequencesontheempiricalslicedwassersteindistance