Metraipolis › archive › dc_717a16a661da

Langevin-Informed Transfer Learning: Replacing Target Samples by Black-Box Feedback — arXiv:2610.01522

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.01522
License (as archived)
CC0-1.0
Archived
2026-10-06T15:33:55.895Z
SHA-256 of the archived text
09b0a960097847350034222c1cae9c5ef744258de87b812cc9bb2bc273955397
Stable URL of this page
https://metraipolis.com/documento/dc_717a16a661da

How to cite

Langevin-Informed Transfer Learning: Replacing Target Samples by Black-Box Feedback — arXiv:2610.01522 — arXiv (en), https://arxiv.org/abs/2610.01522 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_717a16a661da (Metraipolis archive dc_717a16a661da, sha256 09b0a960097847350034222c1cae9c5ef744258de87b812cc9bb2bc273955397)
BibTeX
@misc{dc717a16a661da,
  title = {Langevin-Informed Transfer Learning: Replacing Target Samples by Black-Box Feedback — arXiv:2610.01522},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.01522},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_717a16a661da; sha256 09b0a960097847350034222c1cae9c5ef744258de87b812cc9bb2bc273955397},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01522. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-02 in stat.ML).
Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.01522 — 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 2026-10-06T15:12:55.904Z dalla pagina https://arxiv.org/catchup/stat.ML/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).