Metraipolis › archive › dc_654a71f303e2

Reflected Anchored Langevin Algorithms — arXiv:2610.09522

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09522
License (as archived)
CC0-1.0
Archived
2026-10-08T12:36:56.855Z
SHA-256 of the archived text
8a1e4bd20257e41a569c9244921169a529c9b40b746c23a4ffac7f92532cab83
Stable URL of this page
https://metraipolis.com/documento/dc_654a71f303e2

How to cite

Reflected Anchored Langevin Algorithms — arXiv:2610.09522 — arXiv (en), https://arxiv.org/abs/2610.09522 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_654a71f303e2 (Metraipolis archive dc_654a71f303e2, sha256 8a1e4bd20257e41a569c9244921169a529c9b40b746c23a4ffac7f92532cab83)
BibTeX
@misc{dc654a71f303e2,
  title = {Reflected Anchored Langevin Algorithms — arXiv:2610.09522},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09522},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_654a71f303e2; sha256 8a1e4bd20257e41a569c9244921169a529c9b40b746c23a4ffac7f92532cab83},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09522. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

First order Langevin algorithms for constrained sampling in machine learning, such as projected Langevin Monte Carlo which are based on discretizations of reflected Langevin dynamics, require differentiable log densities that limits their applicability. This paper introduces reflected anchored Langevin dynamics (RALD), a reflected diffusion that converges to non-differentiable targets on constrained domains. The method uses a smooth anchored reference potential and multiplies the drift and noise covariance of its reflected Langevin dynamics by the same state dependent scaling factor. Its Euler-Maruyama discretization with projection gives reflected anchored Langevin Monte Carlo (RALMC) algorithm. We prove explicit convergence bounds and iteration complexity for RALMC in the 2-Wasserstein distance to the target distribution. Numerical experiments are provided to illustrate the theoretical predictions and the empirical performance of the method.

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); Probability (math.PR).
Pagina del lavoro: https://arxiv.org/abs/2610.09522 — 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 2026-10-08T12:14:15.400Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).