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

2023/04/24 by Tanguy, Eloi, Flamary, Rémi, Delon, Julie · 1 citation
#FOS: Mathematics #Probability (math.PR)

paper · doi:10.48550/arxiv.2304.12029

Abstract

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^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 ∑_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.

Cited by

• Slicing Wasserstein Over Wasserstein Via Functional Optimal Transport

Related

• Sliced Wasserstein distance between probability measures on Hilbert spaces
• Wasserstein Distance and the Rectifiability of Doubling Measures: Part I
• Sharp bounds for max-sliced Wasserstein distances
• Fast Approximation of the Sliced-Wasserstein Distance Using\n Concentration of Random Projections
• A Lower Bound on the Sliced Wasserstein Comparison Constant for Translated Measures