Metraipolis › archive › dc_cc7b8b1e2bf5

Poisson-Corrector Complexity Bounds for Moreau--Yosida Unadjusted Langevin Sampling — arXiv:2609.12594

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.12594
License (as archived)
CC0-1.0
Archived
2026-10-16T03:15:49.586Z
SHA-256 of the archived text
71e80092589e75843139209ae296d1355d711d1f75a79bbe36035ec9d37366d2
Stable URL of this page
https://metraipolis.com/documento/dc_cc7b8b1e2bf5

How to cite

Poisson-Corrector Complexity Bounds for Moreau--Yosida Unadjusted Langevin Sampling — arXiv:2609.12594 — arXiv (en), https://arxiv.org/abs/2609.12594 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cc7b8b1e2bf5 (Metraipolis archive dc_cc7b8b1e2bf5, sha256 71e80092589e75843139209ae296d1355d711d1f75a79bbe36035ec9d37366d2)
BibTeX
@misc{dccc7b8b1e2bf5,
  title = {Poisson-Corrector Complexity Bounds for Moreau--Yosida Unadjusted Langevin Sampling — arXiv:2609.12594},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12594},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cc7b8b1e2bf5; sha256 71e80092589e75843139209ae296d1355d711d1f75a79bbe36035ec9d37366d2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12594. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study the classical Moreau--Yosida unadjusted Langevin algorithm (MYULA) for $\pi(\,\mathrm{d} x)\propto e^{-f(x)-g(x)}\,\mathrm{d} x$, where $f\in C^2(\mathbb{R}^d)$ is $m$-strongly convex with $L_f$-Lipschitz gradient and $g:\mathbb{R}^d\to\mathbb{R}$ is convex and globally $G$-Lipschitz. For the Moreau-smoothed target $\pi_\lambda$ and the MYULA invariant law $\widehat\pi_{\lambda,h}$, we prove \[ \sqrt m\,W_2(\pi_\lambda,\widehat\pi_{\lambda,h}) =O(h)+\widetilde O(h^{3/4}) \] under $0<h(L_f+\lambda^{-1})\le c$, with only logarithmic dependence on $\lambda^{-1}$ in the error coefficients. Combining this estimate with the Moreau approximation bias yields $\widetilde O(\varepsilon^{-4/3})$ iterations to achieve $\sqrt m\,W_2(\mu_N,\pi)\le\varepsilon$, for fixed model parameters and initialization. The proof combines a discrete Poisson corrector with active-trace estimates and a shared-noise bound for the exact--Euler two-point curvature.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.12594 — 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 2026-10-16T03:05:44.053Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).