Domain-Decomposed Randomized Neural Networks for Partial Differential Equations in Unbounded Domains

DOI10.48550/arXiv.2606.31342MaRDI QIDQ7270411zbMATH OpenarXivFDO

Authors Haixin Wang, Haoning Dang, Shimin Guo, Fei Wang

Publication date 30 June 2026

Published in arXiv

Tldr We propose a domain-decomposed randomized neural network framework that uses different subnetworks to capture near-field local and geometric features versus far-field exterior decay. This setup allows for effective representation of localized structures, irregular geometries, or solutions with different near-field and far-field behaviors in unbounded domains.

Full work available at URL https://doi.org/10.48550/arXiv.2606.31342

arXiv classification

cs.LGmath.NA

This page was built for publication: Domain-Decomposed Randomized Neural Networks for Partial Differential Equations in Unbounded Domains

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7270411)