Logo image
Efficient Bayesian Physics Informed Neural Networks for Inverse Problems via Ensemble Kalman Inversion
Preprint   Open access

Efficient Bayesian Physics Informed Neural Networks for Inverse Problems via Ensemble Kalman Inversion

Andrew Pensoneault and Xueyu Zhu
ArXiv.org
03/13/2023
DOI: 10.48550/arxiv.2303.07392
url
https://doi.org/10.48550/arxiv.2303.07392View
Preprint (Author's original)This preprint has not been evaluated by subject experts through peer review. Preprints may undergo extensive changes and/or become peer-reviewed journal articles. Open Access

Abstract

Bayesian Physics Informed Neural Networks (B-PINNs) have gained significant attention for inferring physical parameters and learning the forward solutions for problems based on partial differential equations. However, the overparameterized nature of neural networks poses a computational challenge for high-dimensional posterior inference. Existing inference approaches, such as particle-based or variance inference methods, are either computationally expensive for high-dimensional posterior inference or provide unsatisfactory uncertainty estimates. In this paper, we present a new efficient inference algorithm for B-PINNs that uses Ensemble Kalman Inversion (EKI) for high-dimensional inference tasks. We find that our proposed method can achieve inference results with informative uncertainty estimates comparable to Hamiltonian Monte Carlo (HMC)-based B-PINNs with a much reduced computational cost. These findings suggest that our proposed approach has great potential for uncertainty quantification in physics-informed machine learning for practical applications.

Details

Metrics

39 Record Views
Logo image