Metraipolis › archive › dc_ef1030f9635e
Steering Diffusion Models to Rare Events with Sequential Monte Carlo — arXiv:2610.08652
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.08652
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:42:55.078Z
- SHA-256 of the archived text
8169790725e6066314f1316793b2241fba9c991abb0cdf9228dcba0c3a15878d- Stable URL of this page
https://metraipolis.com/documento/dc_ef1030f9635e
How to cite
Steering Diffusion Models to Rare Events with Sequential Monte Carlo — arXiv:2610.08652 — arXiv (en), https://arxiv.org/abs/2610.08652 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ef1030f9635e (Metraipolis archive dc_ef1030f9635e, sha256 8169790725e6066314f1316793b2241fba9c991abb0cdf9228dcba0c3a15878d)
BibTeX
@misc{dcef1030f9635e,
title = {Steering Diffusion Models to Rare Events with Sequential Monte Carlo — arXiv:2610.08652},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.08652},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ef1030f9635e; sha256 8169790725e6066314f1316793b2241fba9c991abb0cdf9228dcba0c3a15878d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08652. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Diffusion models are increasingly used as surrogates for expensive simulators in weather prediction, molecular dynamics, and materials design. In these models, computing the probability $p_0[E]$ of an event $E$ is difficult, especially when the event of interest is rare. A stable estimate using Monte Carlo becomes computationally intractable, requiring a growing sample size $\propto\!1/p_0[E]$ to compensate for an increasing rarity. In this paper, we present Diffusion Importance Sampling of Rare Events or DireSMC, a sequential Monte Carlo scheme that guides a population of weighted samples towards the rare event, giving access not only to samples but also to a calibrated estimate of its probability. We set up our guidance using an analytical relaxation of the event set, allowing the method to easily extend to a wide range of user-defined rare events. We validate our method on a toy problem with analytical solutions and on a score-based climate emulator, where we obtain accurate rare-event probabilities on a range of rarities from $10^{-3}$ to $10^{-5}$, achieving net speed-ups of $9\times$ to $1413\times$ over Monte Carlo.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.08652 — 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 2026-10-07T11:19:24.949Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).