Incorporating Continuous Dependence Qualifies Physics-Informed Neural Networks for Operator Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Guojie, Yang, Wuyue, Hong, Liu
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910074141671424
author Li, Guojie
Yang, Wuyue
Hong, Liu
author_facet Li, Guojie
Yang, Wuyue
Hong, Liu
contents Physics-informed neural networks (PINNs) have been proven as a promising way for solving various partial differential equations, especially high-dimensional ones and those with irregular boundaries. However, their capabilities in real applications are highly restricted by their poor generalization performance. Inspired by the rigorous mathematical statements on the well-posedness of PDEs, we develop a novel extension of PINNs by incorporating the additional information on the continuous dependence of PDE solutions with respect to parameters and initial/boundary values (abbreviated as cd-PINN). Extensive numerical experiments demonstrate that, with limited labeled data, cd-PINN achieves 1-3 orders of magnitude lower in test MSE than DeepONet and FNO. Therefore, incorporating the continuous dependence of PDE solutions provides a simple way for qualifying PINNs for operator learning.
format Preprint
id arxiv_https___arxiv_org_abs_2603_25122
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Incorporating Continuous Dependence Qualifies Physics-Informed Neural Networks for Operator Learning
Li, Guojie
Yang, Wuyue
Hong, Liu
Dynamical Systems
Numerical Analysis
Physics-informed neural networks (PINNs) have been proven as a promising way for solving various partial differential equations, especially high-dimensional ones and those with irregular boundaries. However, their capabilities in real applications are highly restricted by their poor generalization performance. Inspired by the rigorous mathematical statements on the well-posedness of PDEs, we develop a novel extension of PINNs by incorporating the additional information on the continuous dependence of PDE solutions with respect to parameters and initial/boundary values (abbreviated as cd-PINN). Extensive numerical experiments demonstrate that, with limited labeled data, cd-PINN achieves 1-3 orders of magnitude lower in test MSE than DeepONet and FNO. Therefore, incorporating the continuous dependence of PDE solutions provides a simple way for qualifying PINNs for operator learning.
title Incorporating Continuous Dependence Qualifies Physics-Informed Neural Networks for Operator Learning
topic Dynamical Systems
Numerical Analysis
url https://arxiv.org/abs/2603.25122