A primer on variational inference for physics-informed deep generative modelling

Alex Glyn-Davies, Arnaud Vadeboncoeur, O. Deniz Akyildiz, Ieva Kazlauskaite and Mark Girolami

LSE Research Online Documents on Economics from London School of Economics and Political Science, LSE Library

Abstract: Variational inference (VI) is a computationally efficient and scalable methodology for approximate Bayesian inference. It strikes a balance between accuracy of uncertainty quantification and practical tractability. It excels at generative modelling and inversion tasks due to its built-in Bayesian regularization and flexibility, essential qualities for physics-related problems. For such problems, the underlying physical model determines the dependence between variables of interest, which in turn will require a tailored derivation for the central VI learning objective. Furthermore, in many physical inference applications, this structure has rich meaning and is essential for accurately capturing the dynamics of interest. In this paper, we provide an accessible and thorough technical introduction to VI for forward and inverse problems, guiding the reader through standard derivations of the VI framework and how it can best be realized through deep learning. We then review and unify recent literature exemplifying the flexibility allowed by VI. This paper is designed for a general scientific audience looking to solve physics-based problems with an emphasis on uncertainty quantification. This article is part of the theme issue ‘Generative modelling meets Bayesian inference: a new paradigm for inverse problems’.

Keywords: PDE; physics-informed; generative model; deep learning; variational inference (search for similar items in EconPapers)
JEL-codes: C1 (search for similar items in EconPapers)
Pages: 16 pages
Date: 2025-06-19
References: Add references at CitEc
Citations:

Published in Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 19, June, 2025, 383(2299). ISSN: 1364-503X

Downloads: (external link)
http://eprints.lse.ac.uk/128504/ Open access version. (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ehl:lserod:128504

Access Statistics for this paper

More papers in LSE Research Online Documents on Economics from London School of Economics and Political Science, LSE Library LSE Library Portugal Street London, WC2A 2HD, U.K.. Contact information at EDIRC.
Bibliographic data for series maintained by LSERO Manager ().