Bayesian Reasoning for Physics Informed Neural Networks

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Graczyk, Krzysztof M., Witkowski, Kornel
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917541008375808
author Graczyk, Krzysztof M.
Witkowski, Kornel
author_facet Graczyk, Krzysztof M.
Witkowski, Kornel
contents We introduce an evidence-driven Bayesian formulation of physics-informed neural networks that enables automatic optimization of loss weights between PDE residuals, boundary conditions, and observational data. Unlike existing Bayesian PINN approaches based on sampling or variational inference, the proposed method uses a Laplace approximation to compute model evidence analytically, enabling efficient hyperparameter tuning and model comparison without posterior sampling. We demonstrate the method on the heat, wave, and Burgers' equations, obtaining solutions in agreement with exact or reference results. In the Burgers' equation example, we further show that the framework naturally integrates information from governing equations and noisy measurements, providing predictive uncertainties within a unified Bayesian setting.
format Preprint
id arxiv_https___arxiv_org_abs_2308_13222
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Bayesian Reasoning for Physics Informed Neural Networks
Graczyk, Krzysztof M.
Witkowski, Kornel
Computational Physics
Machine Learning
Fluid Dynamics
We introduce an evidence-driven Bayesian formulation of physics-informed neural networks that enables automatic optimization of loss weights between PDE residuals, boundary conditions, and observational data. Unlike existing Bayesian PINN approaches based on sampling or variational inference, the proposed method uses a Laplace approximation to compute model evidence analytically, enabling efficient hyperparameter tuning and model comparison without posterior sampling. We demonstrate the method on the heat, wave, and Burgers' equations, obtaining solutions in agreement with exact or reference results. In the Burgers' equation example, we further show that the framework naturally integrates information from governing equations and noisy measurements, providing predictive uncertainties within a unified Bayesian setting.
title Bayesian Reasoning for Physics Informed Neural Networks
topic Computational Physics
Machine Learning
Fluid Dynamics
url https://arxiv.org/abs/2308.13222