Metraipolis › archive › dc_7cff33891db8

Learning Informative Prior with Infinite-Dimensional Continuous Normalizing Flow for Bayesian Inverse Problem — arXiv:2609.03343

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03343
License (as archived)
CC0-1.0
Archived
2026-10-17T02:08:37.508Z
SHA-256 of the archived text
3af3d2ad1556725bca0ef3f919981fa0832e0831787cadcb91a7bb545561fa51
Stable URL of this page
https://metraipolis.com/documento/dc_7cff33891db8

How to cite

Learning Informative Prior with Infinite-Dimensional Continuous Normalizing Flow for Bayesian Inverse Problem — arXiv:2609.03343 — arXiv (en), https://arxiv.org/abs/2609.03343 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7cff33891db8 (Metraipolis archive dc_7cff33891db8, sha256 3af3d2ad1556725bca0ef3f919981fa0832e0831787cadcb91a7bb545561fa51)
BibTeX
@misc{dc7cff33891db8,
  title = {Learning Informative Prior with Infinite-Dimensional Continuous Normalizing Flow for Bayesian Inverse Problem — arXiv:2609.03343},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03343},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7cff33891db8; sha256 3af3d2ad1556725bca0ef3f919981fa0832e0831787cadcb91a7bb545561fa51},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03343. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper addresses infinite-dimensional Bayesian inference for inverse problem of partial differential equations with model parameters in infinite-dimensional Hilbert space. To effectively incorporate prior information, we propose a novel continuous normalizing flows based infinite-dimensional model. Specifically, by introducing a well-defined neural ordinary differential equation in infinite-dimensional space, a simple reference measure can be transformed into a more complex measure which encodes the prior information. A corresponding theoretical framework is established to ensure the well-posedness of our proposed Bayesian prior in infinite-dimensional space. We also provide training methods of the prior for two distinct data settings, along with two sampling algorithms for the resulting Bayesian posterior. The proposed framework is applied to three representative inverse problems: the simple smooth inverse problem, inverse scattering problem, and the inverse heat conduction problem. Numerical experiments support the theoretical analysis and demonstrate the efficiency of the proposed algorithms.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.LG).
Categorie arXiv: Numerical Analysis (math.NA) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.03343 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T01:47:25.615Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).