Operator Learning Using Random Features: A Tool for Scientific Computing
SIAM Review · 2024-08 · 66 (3) · 535-571
DOI: 10.1137/24m1648703 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Review, online erschienen am 08.08.2024. Verfasst von Nicholas H. Nelsen und 1 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 152 Literaturangaben. Gefördert von: Office of Naval Research, National Science Foundation.
Abstract (Originalsprache)
Supervised operator learning centers on the use of training data, in the form of input-output pairs, to estimate maps between infinite-dimensional spaces. It is emerging as a powerful tool to complement traditional scientific computing, which may often be framed in terms of operators mapping between spaces of functions. Building on the classical random features methodology for scalar regression, this paper introduces the function-valued random features method. This leads to a supervised operator learning architecture that is practical for nonlinear problems yet is structured enough to facilitate efficient training through the optimization of a convex, quadratic cost. Due to the quadratic structure, the trained model is equipped with convergence guarantees and error and complexity bounds, properties that are not readily available for most other operator learning architectures. At its core, the proposed approach builds a linear combination of random operators. This turns out to be a low-rank approximation of an operator-valued kernel ridge regression algorithm, and hence the method also has strong connections to Gaussian process regression. The paper designs function-valued random features that are tailored to the structure of two nonlinear operator learning benchmark problems arising from parametric partial differential equations. Numerical results demonstrate the scalability, discretization invariance, and transferability of the function-valued random features method.
Förderung
- Office of Naval Research
- National Science Foundation
Zitieren
APA
Nelsen, N. H., & Stuart, A. M. (2024). Operator Learning Using Random Features: A Tool for Scientific Computing. SIAM Review, 66(3), 535-571. https://doi.org/10.1137/24m1648703
Vancouver
Nelsen NH, Stuart AM. Operator Learning Using Random Features: A Tool for Scientific Computing. SIAM Review. 2024;66(3):535-571. doi:10.1137/24m1648703
BibTeX
@article{Nelsen2024,
author = {Nelsen, Nicholas H. and Stuart, Andrew M.},
title = {Operator Learning Using Random Features: A Tool for Scientific Computing},
journal = {SIAM Review},
year = {2024},
volume = {66},
number = {3},
pages = {535--571},
doi = {10.1137/24m1648703}
}
EUVIMED