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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tanguy, Eloi, Flamary, Rémi, Delon, Julie
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912542163468288
author Tanguy, Eloi
Flamary, Rémi
Delon, Julie
author_facet Tanguy, Eloi
Flamary, Rémi
Delon, Julie
contents This paper deals with the reconstruction of a discrete measure $γ_Z$ on $\mathbb{R}^d$ from the knowledge of its pushforward measures $P_i\#γ_Z$ by linear applications $P_i: \mathbb{R}^d \rightarrow \mathbb{R}^{d_i}$ (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 $\sum_i d_i > d$, 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.
format Preprint
id arxiv_https___arxiv_org_abs_2304_12029
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Reconstructing discrete measures from projections. Consequences on the empirical Sliced Wasserstein Distance
Tanguy, Eloi
Flamary, Rémi
Delon, Julie
Probability
This paper deals with the reconstruction of a discrete measure $γ_Z$ on $\mathbb{R}^d$ from the knowledge of its pushforward measures $P_i\#γ_Z$ by linear applications $P_i: \mathbb{R}^d \rightarrow \mathbb{R}^{d_i}$ (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 $\sum_i d_i > d$, 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.
title Reconstructing discrete measures from projections. Consequences on the empirical Sliced Wasserstein Distance
topic Probability
url https://arxiv.org/abs/2304.12029