A Localized Basis Structure in Physics-Informed Neural Network for Solving Elliptic Problems

We present physics-informed neural network (PINN) approaches for solving elliptic boundary value problems with improved stability and accuracy. Standard PINNs based on multilayer perceptrons often exhibit limited approximation power and unstable convergence, particularly when trained with second-order optimization methods. To overcome these issues, we propose a family of localized basis-inspired architectures specifically designed to work effectively with the Levenberg–Marquardt (LM) optimizer. The Localized Basis Net (LBN) employs localized units with interpretable parameters, the extended LBN (XLBN) augments this structure with nonlinear mixing for enhanced flexibility, and the Fixed Basis Net (FBN) is a variant of XLBN where basis-related parameters are fixed to isolate and evaluate the effect of learning basis functions. We also establish the approximation capability of LBNs in Sobolev norms. Numerical experiments show that the proposed networks, when coupled with LM, achieve robust convergence and higher accuracy for a variety of elliptic problems, including linear, multiscale coefficient, and nonlinear p-Laplacian equations. These results demonstrate that network–optimizer co-design provides a promising direction for developing reliable and interpretable neural network methods in scientific computing.

Authors

Institutions

Publication Details

Journal
Advances in Applied Mathematics and Mechanics
Published
2026-11-12
DOI
https://doi.org/10.4208/aamm.oa-2025-0312
Primary Topic
Model Reduction and Neural Networks
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A Localized Basis Structure in Physics-Informed Neural Network for Solving Elliptic Problems

Hyeokjoo Park, Deok-Kyu Jang, Gwanghyun Jo
Advances in Applied Mathematics and Mechanics
Model Reduction and Neural Networks
article

A Localized Basis Structure in Physics-Informed Neural Network for Solving Elliptic Problems

Hyeokjoo Park, Deok-Kyu Jang, Gwanghyun Jo
article en

Abstract

We present physics-informed neural network (PINN) approaches for solving elliptic boundary value problems with improved stability and accuracy. Standard PINNs based on multilayer perceptrons often exhibit limited approximation power and unstable convergence, particularly when trained with second-order optimization methods. To overcome these issues, we propose a family of localized basis-inspired architectures specifically designed to work effectively with the Levenberg–Marquardt (LM) optimizer. The Localized Basis Net (LBN) employs localized units with interpretable parameters, the extended LBN (XLBN) augments this structure with nonlinear mixing for enhanced flexibility, and the Fixed Basis Net (FBN) is a variant of XLBN where basis-related parameters are fixed to isolate and evaluate the effect of learning basis functions. We also establish the approximation capability of LBNs in Sobolev norms. Numerical experiments show that the proposed networks, when coupled with LM, achieve robust convergence and higher accuracy for a variety of elliptic problems, including linear, multiscale coefficient, and nonlinear p-Laplacian equations. These results demonstrate that network–optimizer co-design provides a promising direction for developing reliable and interpretable neural network methods in scientific computing.

Advances in Applied Mathematics and MechanicsVol. 19(3)
Kangwon National University (KR), Korea University (KR), Hanyang University (KR)
National Research Foundation of Korea
Model Reduction and Neural Networks
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon