{
  "abstract": "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 rare event sampling with Sequential Monte Carlo (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.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.08652",
  "author_total": 6,
  "authors": [
    {
      "name": "Aavash Subedi"
    },
    {
      "name": "Tim Reichelt"
    },
    {
      "name": "Christopher Williams"
    },
    {
      "name": "Philip Stier"
    },
    {
      "name": "Yee Whye Teh"
    },
    {
      "name": "Saifuddin Syed"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/1ey474wd2m97x.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.08652",
  "fulltext_url": null,
  "id": "1ey474wd2m97x",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.08652",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "2613|Markov Chains and Monte Carlo Methods"
    ]
  ],
  "openalex": "W7221051864",
  "pdf_url": "https://arxiv.org/pdf/2610.08652",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-13",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/1ey474wd2m97x.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:29:42Z",
      "native_id": "2610.08652",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.08652"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Steering Diffusion Models to Rare Events with Sequential Monte Carlo",
  "title_text": "Steering Diffusion Models to Rare Events with Sequential Monte Carlo",
  "type": "preprint",
  "updated_at": "2026-10-30T12:29:42Z",
  "url": "https://research.draconitic.com/paper/1ey474wd2m97x",
  "venue": "arXiv",
  "versions": []
}