Near-optimal estimation of smooth transport maps with kernel sums-of-squares - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles SIAM Journal on Mathematics of Data Science Year : 2024

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

Abstract

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
Origin Files produced by the author(s)

Dates and versions

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

Identifiers

Cite

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⟩
96 View
80 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More