Near-optimal estimation of smooth transport maps with kernel sums-of-squares - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue SIAM Journal on Mathematics of Data Science Année : 2024

Near-optimal estimation of smooth transport maps with kernel sums-of-squares

Résumé

It was recently shown that under smoothness conditions, the squared Wasserstein distance between two distributions could be efficiently computed with appealing statistical error upper bounds. However, rather than the distance itself, the object of interest for applications such as generative modeling is the underlying optimal transport map. Hence, computational and statistical guarantees need to be obtained for the estimated maps themselves. In this paper, we propose the first tractable algorithm for which the statistical $L^2$ error on the maps nearly matches the existing minimax lower-bounds for smooth map estimation. Our method is based on solving the semi-dual formulation of optimal transport with an infinite-dimensional sum-of-squares reformulation, and leads to an algorithm which has dimension-free polynomial rates in the number of samples, with potentially exponentially dimension-dependent constants.
Fichier principal
Vignette du fichier
ArXiv__Convergence_of_potentials (8).pdf (658.47 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03466696 , version 1 (06-12-2021)

Identifiants

Citer

Boris Muzellec, Adrien Vacher, Francis Bach, François-Xavier Vialard, Alessandro Rudi. Near-optimal estimation of smooth transport maps with kernel sums-of-squares. SIAM Journal on Mathematics of Data Science, In press. ⟨hal-03466696⟩
93 Consultations
71 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More