A Unified Framework for the Error Analysis of Physics-Informed Neural Networks
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911791301263360 |
|---|---|
| author | Zeinhofer, Marius Masri, Rami Mardal, Kent-André |
| author_facet | Zeinhofer, Marius Masri, Rami Mardal, Kent-André |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_00529 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | A Unified Framework for the Error Analysis of Physics-Informed Neural Networks Zeinhofer, Marius Masri, Rami Mardal, Kent-André Numerical Analysis 65M12, 65M15 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. |
| title | A Unified Framework for the Error Analysis of Physics-Informed Neural Networks |
| topic | Numerical Analysis 65M12, 65M15 |
| url | https://arxiv.org/abs/2311.00529 |