Guardado en:
Detalles Bibliográficos
Autores principales: Ko, Gyounghun, Son, Sung-Jun, Cho, Seung Yeon, Lee, Myeong-Su
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2604.04971
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911571166363648
author Ko, Gyounghun
Son, Sung-Jun
Cho, Seung Yeon
Lee, Myeong-Su
author_facet Ko, Gyounghun
Son, Sung-Jun
Cho, Seung Yeon
Lee, Myeong-Su
contents While Physics-Informed Neural Networks offer a promising framework for solving partial differential equations, the standard $L^2$ loss formulation is fundamentally insufficient when applied to the Bhatnagar-Gross-Krook (BGK) model. Specifically, simply minimizing the standard loss does not guarantee accurate predictions of the macroscopic moments, causing the approximate solutions to fail in capturing the true physical solution. To overcome this limitation, we introduce a velocity-weighted $L^2$ loss function designed to effectively penalize errors in the high-velocity regions. By establishing a stability estimate for the proposed approach, we shows that minimizing the proposed weighted loss guarantees the convergence of the approximate solution. Also, numerical experiments demonstrate that employing this weighted PINN loss leads to superior accuracy and robustness across various benchmarks compared to the standard approach.
format Preprint
id arxiv_https___arxiv_org_abs_2604_04971
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Theory-guided Weighted $L^2$ Loss for solving the BGK model via Physics-informed neural networks
Ko, Gyounghun
Son, Sung-Jun
Cho, Seung Yeon
Lee, Myeong-Su
Machine Learning
Numerical Analysis
Computational Physics
68T07 (Primary) 82C40, 65M12, 65M70, 65M99 (Secondary)
While Physics-Informed Neural Networks offer a promising framework for solving partial differential equations, the standard $L^2$ loss formulation is fundamentally insufficient when applied to the Bhatnagar-Gross-Krook (BGK) model. Specifically, simply minimizing the standard loss does not guarantee accurate predictions of the macroscopic moments, causing the approximate solutions to fail in capturing the true physical solution. To overcome this limitation, we introduce a velocity-weighted $L^2$ loss function designed to effectively penalize errors in the high-velocity regions. By establishing a stability estimate for the proposed approach, we shows that minimizing the proposed weighted loss guarantees the convergence of the approximate solution. Also, numerical experiments demonstrate that employing this weighted PINN loss leads to superior accuracy and robustness across various benchmarks compared to the standard approach.
title A Theory-guided Weighted $L^2$ Loss for solving the BGK model via Physics-informed neural networks
topic Machine Learning
Numerical Analysis
Computational Physics
68T07 (Primary) 82C40, 65M12, 65M70, 65M99 (Secondary)
url https://arxiv.org/abs/2604.04971