Multiscale Neural Networks for Approximating Green’s Functions
SIAM Journal on Scientific Computing · 30.04.2026 · 48 (2) · C240-C270
DOI: 10.1137/24m1709601 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Scientific Computing, online erschienen am 06.04.2026. Verfasst von Wenrui Hao und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 79 Literaturangaben. Gefördert von: Lawrence Livermore National Laboratory, National Institute of General Medical Sciences, National Science Foundation.
Abstract (Originalsprache)
Neural networks (NNs) have been widely used to solve partial differential equations (PDEs) in the applications of physics, biology, and engineering. One effective approach for solving PDEs with a fixed differential operator is learning Green’s functions. However, Green’s functions are notoriously difficult to learn due to their poor regularity, which typically requires larger NNs and longer training times. In this paper, we address these challenges by leveraging multiscale NNs to learn Green’s functions. Through theoretical analysis using multiscale Barron space methods and experimental validation, we show that the multiscale approach significantly reduces the necessary NN size and accelerates training.
Förderung
- Lawrence Livermore National Laboratory
- National Institute of General Medical Sciences
- National Science Foundation
Zitieren
APA
Hao, W., Li, R. P., Xi, Y., Xu, T., & Yang, Y. (2026). Multiscale Neural Networks for Approximating Green’s Functions. SIAM Journal on Scientific Computing, 48(2), C240-C270. https://doi.org/10.1137/24m1709601
Vancouver
Hao W, Li RP, Xi Y, Xu T, Yang Y. Multiscale Neural Networks for Approximating Green’s Functions. SIAM Journal on Scientific Computing. 2026;48(2):C240-C270. doi:10.1137/24m1709601
BibTeX
@article{Hao2026,
author = {Hao, Wenrui and Li, Rui Peng and Xi, Yuanzhe and Xu, Tianshi and Yang, Yahong},
title = {Multiscale Neural Networks for Approximating Green’s Functions},
journal = {SIAM Journal on Scientific Computing},
year = {2026},
volume = {48},
number = {2},
pages = {C240--C270},
doi = {10.1137/24m1709601}
}
EUVIMED