Metraipolis › archive › dc_d8075faa6f83
Conformal Prediction for Time-Dependent PDEs — arXiv:2611.08409
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.08409
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-06T14:50:59.732Z
- SHA-256 of the archived text
b95122920c8172ba4dc9134b535f9beda28aeb5f13a5f6a93a3001f4861a2dd2- Stable URL of this page
https://metraipolis.com/documento/dc_d8075faa6f83
How to cite
Conformal Prediction for Time-Dependent PDEs — arXiv:2611.08409 — arXiv (en), https://arxiv.org/abs/2611.08409 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d8075faa6f83 (Metraipolis archive dc_d8075faa6f83, sha256 b95122920c8172ba4dc9134b535f9beda28aeb5f13a5f6a93a3001f4861a2dd2)
BibTeX
@misc{dcd8075faa6f83,
title = {Conformal Prediction for Time-Dependent PDEs — arXiv:2611.08409},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.08409},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d8075faa6f83; sha256 b95122920c8172ba4dc9134b535f9beda28aeb5f13a5f6a93a3001f4861a2dd2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08409. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Uncertainty quantification is crucial in scientific machine learning, where models inform safety-critical tasks such as flood forecasting, financial risk management, and thermal control in machines. Conformal prediction provides distribution-free coverage guarantees, but in time-dependent settings common to physics and engineering, these guarantees can break down, leading to systematic undercoverage. We study this problem in the context of surrogate models for time-dependent physical systems described by partial differential equations. We prove that in a function space setting, distributions at arbitrarily close times can be mutually singular, making exact coverage guarantees impossible. We further show that in discretized settings, the total variation distance between distributions often saturates exponentially fast with the grid resolution, mandating restrictions on the spatial discretization to ensure coverage. Finally, for certain settings, we show how to use principled weighted conformal prediction to obtain finite-sample coverage guarantees over growing time horizons. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2611.08409 — 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 2026-11-06T14:21:42.649Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).