An Optimal Weighted Least-Squares Method for Operator Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Turnage, John, Lowery, Matthew, Jakeman, John, Morrow, Zachary, Narayan, Akil, Shankar, Varun
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911315607420928
author Turnage, John
Lowery, Matthew
Jakeman, John
Morrow, Zachary
Narayan, Akil
Shankar, Varun
author_facet Turnage, John
Lowery, Matthew
Jakeman, John
Morrow, Zachary
Narayan, Akil
Shankar, Varun
contents We consider the problem of learning an unknown, possibly nonlinear operator between separable Hilbert spaces from supervised data. Inputs are drawn from a prescribed probability measure on the input space, and outputs are (possibly noisy) evaluations of the target operator. We regard admissible operators as square-integrable maps with respect to a fixed approximation measure, and we measure reconstruction error in the corresponding Bochner norm. For a finite-dimensional approximation space $V$ of dimension $N$, we study weighted least squares estimators in $V$ and establish probabilistic stability and accuracy bounds in the Bochner norm. We show that there exist sampling measures and weights - defined via an operator-level Christoffel function - that yield uniformly well-conditioned Gram matrices and near-optimal sample complexity, with a number of training samples $M$ on the order of $N \log N$. We complement the analysis by constructing explicit operator approximation spaces in cases of interest: rank-one linear operators that are dense in the class of bounded linear operators, and rank-one polynomial operators that are dense in the Bochner space under mild assumptions on the approximation measure. For both families we describe implementable procedures for sampling from the associated optimal measures. Finally, we demonstrate the effectiveness of this framework on several benchmark problems, including learning solution operators for the Poisson equation, viscous Burgers' equation, and the incompressible Navier-Stokes equations.
format Preprint
id arxiv_https___arxiv_org_abs_2512_11168
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An Optimal Weighted Least-Squares Method for Operator Learning
Turnage, John
Lowery, Matthew
Jakeman, John
Morrow, Zachary
Narayan, Akil
Shankar, Varun
Numerical Analysis
65D15 (primary) 65C20, 41A35, 41A81, 41A10 (secondary)
We consider the problem of learning an unknown, possibly nonlinear operator between separable Hilbert spaces from supervised data. Inputs are drawn from a prescribed probability measure on the input space, and outputs are (possibly noisy) evaluations of the target operator. We regard admissible operators as square-integrable maps with respect to a fixed approximation measure, and we measure reconstruction error in the corresponding Bochner norm. For a finite-dimensional approximation space $V$ of dimension $N$, we study weighted least squares estimators in $V$ and establish probabilistic stability and accuracy bounds in the Bochner norm. We show that there exist sampling measures and weights - defined via an operator-level Christoffel function - that yield uniformly well-conditioned Gram matrices and near-optimal sample complexity, with a number of training samples $M$ on the order of $N \log N$. We complement the analysis by constructing explicit operator approximation spaces in cases of interest: rank-one linear operators that are dense in the class of bounded linear operators, and rank-one polynomial operators that are dense in the Bochner space under mild assumptions on the approximation measure. For both families we describe implementable procedures for sampling from the associated optimal measures. Finally, we demonstrate the effectiveness of this framework on several benchmark problems, including learning solution operators for the Poisson equation, viscous Burgers' equation, and the incompressible Navier-Stokes equations.
title An Optimal Weighted Least-Squares Method for Operator Learning
topic Numerical Analysis
65D15 (primary) 65C20, 41A35, 41A81, 41A10 (secondary)
url https://arxiv.org/abs/2512.11168