{
  "abstract": "We study Bayesian posterior sampling when the likelihood is an expectation that is costly to evaluate. We construct a likelihood-free Schrödinger--Föllmer sampler whose drift is written as a ratio of expectations over Gaussian variables and simulator outputs and is estimated directly from joint draws of the two. Importance sampling with a fixed proposal allows the simulator outputs to be generated once and reused across all time steps and trajectories. For the likelihood-free Schrödinger--Föllmer sampler, which draws new Monte Carlo samples at each step, we bound the terminal Wasserstein error under regularity and moment assumptions, separating time-discretization and integration errors. For the likelihood-free Schrödinger--Föllmer sampler with sample reuse, we prove that the output converges to the posterior in the Wasserstein distance, assuming only a finite posterior second moment. Numerical experiments illustrate the reduction in simulator calls and the benefits of randomized quasi-Monte Carlo for drift estimation.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2611.01271",
  "author_total": 3,
  "authors": [
    {
      "name": "Xihan Ren"
    },
    {
      "name": "Zhijian He"
    },
    {
      "name": "Du Ouyang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/55q890nvemedy.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2611.01271",
  "fulltext_url": null,
  "id": "55q890nvemedy",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2611.01271",
  "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",
      "stat.CO"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2611.01271",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/55q890nvemedy.ris",
  "sources": [
    {
      "first_seen": "2026-11-03T12:21:21Z",
      "native_id": "2611.01271",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2611.01271"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.CO",
      "subfield": "statistics"
    }
  ],
  "title": "Likelihood-Free Schrödinger--Föllmer Sampling for Bayesian Inference with Fixed-Proposal Reuse",
  "title_text": "Likelihood-Free Schrödinger--Föllmer Sampling for Bayesian Inference with Fixed-Proposal Reuse",
  "type": "preprint",
  "updated_at": "2026-11-05T15:20:35Z",
  "url": "https://research.draconitic.com/paper/55q890nvemedy",
  "venue": "arXiv",
  "versions": []
}