Quantitative Stability of Optimal Transport Maps under Variations of the Target Measure - Archive ouverte HAL
Article Dans Une Revue Duke Mathematical Journal Année : 2023

Quantitative Stability of Optimal Transport Maps under Variations of the Target Measure

Résumé

This work studies the quantitative stability of the quadratic optimal transport map between a fixed probability density ρ and a probability measure µ on R^d , which we denote Tµ. Assuming that the source density ρ is bounded from above and below on a compact convex set, we prove that the map µ → Tµ is bi-Hölder continuous on large families of probability measures, such as the set of probability measures whose moment of order p > d is bounded by some constant. These stability estimates show that the linearized optimal transport metric W2,ρ(µ, ν) = Tµ − Tν L 2 (ρ,R d) is bi-Hölder equivalent to the 2-Wasserstein distance on such sets, justifiying its use in applications.
Fichier principal
Vignette du fichier
main.pdf (507.63 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03164147 , version 1 (09-03-2021)
hal-03164147 , version 2 (08-03-2023)

Identifiants

Citer

Alex Delalande, Quentin Merigot. Quantitative Stability of Optimal Transport Maps under Variations of the Target Measure. Duke Mathematical Journal, 2023, ⟨10.1215/00127094-2022-0106⟩. ⟨hal-03164147v2⟩
154 Consultations
471 Téléchargements

Altmetric

Partager

More