English

Error estimates of residual minimization using neural networks for linear PDEs

Numerical Analysis 2023-10-04 v3 Numerical Analysis

Abstract

We propose an abstract framework for analyzing the convergence of least-squares methods based on residual minimization when feasible solutions are neural networks. With the norm relations and compactness arguments, we derive error estimates for both continuous and discrete formulations of residual minimization in strong and weak forms. The formulations cover recently developed physics-informed neural networks based on strong and variational formulations.

Keywords

Cite

@article{arxiv.2010.08019,
  title  = {Error estimates of residual minimization using neural networks for linear PDEs},
  author = {Yeonjong Shin and Zhongqiang Zhang and George Em Karniadakis},
  journal= {arXiv preprint arXiv:2010.08019},
  year   = {2023}
}
R2 v1 2026-06-23T19:23:17.814Z