Metraipolis › archive › dc_e4573d975eab

Generative Priors Conditioned on Natural Language for Bayesian Inversion in PDEs — arXiv:2609.32941

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32941
License (as archived)
CC0-1.0
Archived
2026-10-07T22:37:00.757Z
SHA-256 of the archived text
046b541fc50c1c3d704580b2192ddcce874d6d9978343a77baf86542ec40a8ff
Stable URL of this page
https://metraipolis.com/documento/dc_e4573d975eab

How to cite

Generative Priors Conditioned on Natural Language for Bayesian Inversion in PDEs — arXiv:2609.32941 — arXiv (en), https://arxiv.org/abs/2609.32941 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e4573d975eab (Metraipolis archive dc_e4573d975eab, sha256 046b541fc50c1c3d704580b2192ddcce874d6d9978343a77baf86542ec40a8ff)
BibTeX
@misc{dce4573d975eab,
  title = {Generative Priors Conditioned on Natural Language for Bayesian Inversion in PDEs — arXiv:2609.32941},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32941},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e4573d975eab; sha256 046b541fc50c1c3d704580b2192ddcce874d6d9978343a77baf86542ec40a8ff},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32941. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Inferring quantities of interest (QoI) from data is a central task in Science and Engineering. In such contexts, we often have access to both quantitative data and qualitative data. Quantitative data may be represented by noisy sensor measurements, simulation data, re-analysis data; qualitative data may be in the form of text descriptions of experimental setups, expected experiment outcomes, and human-perceived system behaviours. The task we address in this paper is the following. Given a training set of paired qualitative text and quantitative QoI data, we learn to exploit the inherent correlation between the two modalities to learn a highly informative data-driven natural-language-conditional Bayesian prior, such that when presented with a new physical system, we can coherently combine (i) the training dataset, (ii) qualitative text describing the new system, and (iii) a small number of noisy sensor readings from that new system, to perform inference and uncertainty quantification (UQ) over the QoI. To achieve this task, we develop two parallel approaches, one uses conditional diffusion and the other conditional autoencoders, and compare both against classical Bayesian methodology, unconditional generative models and deterministic supervised methods. Each approach has specific strengths and tradeoffs; conditional autoencoder offers theoretical tractability, allows for fast posterior sampling, and provides better-calibrated UQ, whereas conditional diffusion is explored for greater expressiveness and capturing complex posteriors with irregular QoI fields. The approach is tested on the steady-state heat equation, damped Helmholtz equation, and UK weather reanalysis data.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.32941 — 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 2026-10-07T22:14:27.819Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).