Skip to content
Preprint

Sieve Estimation of Optimal Transport Maps from Paired Data in Gaussian Spaces

Sep 2026 · 0 citations
Mathematics

TL;DR

This work analyzes a continuous two-groups model with Gaussian--Laplace mixtures and derives a prediction-risk bound for the resulting transport-map estimator, thereby reducing the problem to finite-dimensional empirical risk minimization.

Abstract

We study the estimation of infinite-dimensional optimal transport maps from noisy paired observations. The population map pushes a Gaussian reference measure forward to a target probability measure on a function space and takes the Cameron--Martin gradient form $T=I+\nabla_{\mathcal H}\phi$. Our estimator uses cylindrical gradient sieves based on finitely many Cameron--Martin coordinates, thereby reducing the problem to finite-dimensional empirical risk minimization. A local nonasymptotic oracle inequality separates cylindrical approximation and statistical estimation errors while accounting for the conditioning of the parametrization. The approximation analysis relies on regularity conditions governing coordinate decay and dependence on omitted input coordinates. For diagonal Gaussian and nonlinear block-interaction classes, we derive matching upper and lower bounds that establish the minimax rate $N^{-s/(2s+1)}$ in expected norm, where $s$ measures weighted coordinate regularity. We further analyze a continuous two-groups model with Gaussian--Laplace mixtures and derive a prediction-risk bound for the resulting transport-map estimator.

View source

Similar papers

Preprint Sep 2026

Approximating Measures on Function Spaces: Transport and Truncation

This work introduces the class $\mathcal{P}_\psi(\mu)$ of measures that differ from a reference measure only through a finite-dimensional map $\psi$ while preserving the reference conditionals on its fibers, and develops approximation theory for fitting within it.

R. Baptista, Bamdad Hosseini, Alexander Hsu · 0 citations
Preprint Oct 2026

Spatial Functional $k$-Nearest-Neighbour Regression under Polynomial Dependence

This paper investigates non-parametric regression estimation when the explanatory variable takes values in a separable Hilbert space and observations are sampled over an increasing regular spatial lattice. Under a rigorous field-to-field independence setup between covariates and errors, we explore the structural and as...

Stéphane Bouka · 0 citations
Preprint Aug 2026

High-Dimensional Spectral Limits for Gaussian KL-Unbalanced Optimal Transport

We study high-dimensional random-matrix limits of Gaussian Kullback--Leibler unbalanced optimal transport (KL-UOT). Under equal marginal penalties, the covariance action admits an exact log-determinant representation in terms of a nonlinear ridge product, together with a positive-semidefinite extension that remains fin...

Jia-Ping Yang, Yun-Xin Zhang · 0 citations
Preprint Oct 2026

Quantitative stability of optimal transport via regularization

We prove quantitative stability estimates for quadratic optimal transport maps by regularizing a Brenier potential and estimating the error in the duality gap. The source has an $L^p$ density, $p>1$, relative to a probability measure with a BV density. When one target lies in a fixed ball, we obtain the $W_2$ H\"older...

Song-Bo Wang, Xiao-Zhen Wang · 1 citation
Preprint Sep 2026

Sharp Gaussian Asymptotics for Marginals of Euclidean Balls

We study Gaussian approximation for probability measures obtained by normalizing one-dimensional profile functions, with one-dimensional marginals of Euclidean balls as the principal example. We first establish quantitative concentration estimates near the set of maximizers. For profiles with a unique nondegenerate max...

Bo-Si Chen, Yen-Chang Huang · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.