EUVIMEDEUVIMED entdecken
Crossref

A unified framework for the error analysis of physics-informed neural networks

Marius Zeinhofer, Rami Masri, Kent–André Mardal

IMA Journal of Numerical Analysis · 26.07.2025 · 45 (5) · 2988-3025

DOI: 10.1093/imanum/drae081 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IMA Journal of Numerical Analysis, online erschienen am 19.11.2024. Verfasst von Marius Zeinhofer und 2 weiteren Autor:innen. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 55 Literaturangaben. Gefördert von: European Research Council, Research Council of Norway.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We prove a priori and a posteriori error estimates for physics-informed neural networks (PINNs) for linear PDEs. We analyze elliptic equations in primal and mixed form, elasticity, parabolic, hyperbolic and Stokes equations, and a PDE constrained optimization problem. For the analysis, we propose an abstract framework in the common language of bilinear forms, and we show that coercivity and continuity lead to error estimates. The obtained estimates are sharp and reveal that the $L^{2}$ penalty approach for initial and boundary conditions in the PINN formulation weakens the norm of the error decay. Finally, utilizing recent advances in PINN optimization, we present numerical examples that illustrate the ability of the method to achieve accurate solutions.

Förderung

  • European Research Council
  • Research Council of Norway

Zitieren

APA

Zeinhofer, M., Masri, R., & Mardal, K. (2025). A unified framework for the error analysis of physics-informed neural networks. IMA Journal of Numerical Analysis, 45(5), 2988-3025. https://doi.org/10.1093/imanum/drae081

Vancouver

Zeinhofer M, Masri R, Mardal K. A unified framework for the error analysis of physics-informed neural networks. IMA Journal of Numerical Analysis. 2025;45(5):2988-3025. doi:10.1093/imanum/drae081

BibTeX
@article{Zeinhofer2025,
  author = {Zeinhofer, Marius and Masri, Rami and Mardal, Kent–André},
  title = {A unified framework for the error analysis of physics-informed neural networks},
  journal = {IMA Journal of Numerical Analysis},
  year = {2025},
  volume = {45},
  number = {5},
  pages = {2988--3025},
  doi = {10.1093/imanum/drae081}
}
Kostenlos starten →