{
  "abstract": "Many scientific and machine learning systems, from molecular dynamics to diffusion models and beyond, are governed by stochastic dynamics with low-dimensional structure, evolving on slow timescales. However, target trajectories, used to identify and interpret such dynamics, are often inaccessible: only biased or static samples that explore the underlying manifold are available. We introduce Langevin-Informed Transfer Learning (LITL), a framework for recovering target Langevin dynamics from biased source samples using only black-box feedback. LITL learns the leading spectral structure of the target infinitesimal generator and the projected drift through Dirichlet representation learning, enabling kinetic reconstruction in spectral form and slow-manifold gradient field estimation. We further introduce a spherical variant well suited to steering normalized latent representations commonly used in learning systems toward desired objectives. We establish finite-sample guarantees for eigenvalue, eigenfunction, and projected drift estimation in Sobolev norms, thereby ensuring generalization of these quantities and their first-order derivatives. Empirically, LITL recovers physical transition timescales from biased molecular simulations, builds kinetic structure from static samples of generative models, reconstructs spherical symmetries of physical systems, and enables post-hoc latent steering of trained neural networks under black-box feedback. Together, these results position spectral operator learning as a practical framework for recovering stochastic dynamics under distribution shift and unlock applications across machine learning and the physical sciences.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.01522",
  "author_total": 6,
  "authors": [
    {
      "name": "Vladimir R. Kostic"
    },
    {
      "name": "Karim Lounici"
    },
    {
      "name": "Hélène Halconruy"
    },
    {
      "name": "Timothée Devergne"
    },
    {
      "name": "Michele Parrinello"
    },
    {
      "name": "Massimiliano Pontil"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/cyec95yf028m0.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.01522",
  "fulltext_url": null,
  "id": "cyec95yf028m0",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.01522",
  "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",
      "3109|Model Reduction and Neural Networks"
    ]
  ],
  "openalex": "W7216343143",
  "pdf_url": "https://arxiv.org/pdf/2610.01522",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/cyec95yf028m0.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:26:14Z",
      "native_id": "2610.01522",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.01522"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Langevin-Informed Transfer Learning: Replacing Target Samples by Black-Box Feedback",
  "title_text": "Langevin-Informed Transfer Learning: Replacing Target Samples by Black-Box Feedback",
  "type": "preprint",
  "updated_at": "2026-10-30T12:26:14Z",
  "url": "https://research.draconitic.com/paper/cyec95yf028m0",
  "venue": "arXiv",
  "versions": []
}