A Locally Conservative Enriched Linearized Neural Network Approximation to Elliptic PDEs

DOI10.48550/ARXIV.2610.04524MaRDI QIDQ7367470arXivFDO

Authors Seungil Kim, Gwanghyun Jo, Young-Ju Lee, Young Ju Lee

Publication date 3 October 2026

Published in arXiv

Tldr We develop an enriched linearized shallow ReLU^k neural network for Darcy flow model that is locally conservative. We prove optimal $H^1$ error estimate and provide numerical evidence.

Full work available at URL https://doi.org/10.48550/ARXIV.2610.04524

arXiv classification

math.NA

This page was built for publication: A Locally Conservative Enriched Linearized Neural Network Approximation to Elliptic PDEs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7367470)