Physics Informed Random Feature Neural Networks for Solving PDEs

DOI10.48550/arXiv.2609.16406MaRDI QIDQ7345479arXivFDO

Authors Chi-An Chen, Chunyang Liao, Ming Zhong

Publication date 14 September 2026

Published in arXiv

Tldr We introduce a physics-informed random feature method that reduces the computational complexity of PINN-based solvers and derives high-probability error bounds on the $H^1$ norm through rigorous approximation error analysis, showing faster error decay rates compared to state-of-the-art PINN-based solvers.

Full work available at URL https://doi.org/10.48550/arXiv.2609.16406

arXiv classification

cs.LGmath.NA

This page was built for publication: Physics Informed Random Feature Neural Networks for Solving PDEs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7345479)