Metraipolis › archive › dc_ffbfb14983f9
A Unified Framework for Wasserstein Convergence of ULMC Methods beyond Log-Concavity: Old and New — arXiv:2609.20713
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.20713
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T04:21:07.859Z
- SHA-256 of the archived text
5897074f4e257056bf6361ede6c07072c2ad37b754e943c31f6c9452b66336bd- Stable URL of this page
https://metraipolis.com/documento/dc_ffbfb14983f9
How to cite
A Unified Framework for Wasserstein Convergence of ULMC Methods beyond Log-Concavity: Old and New — arXiv:2609.20713 — arXiv (en), https://arxiv.org/abs/2609.20713 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ffbfb14983f9 (Metraipolis archive dc_ffbfb14983f9, sha256 5897074f4e257056bf6361ede6c07072c2ad37b754e943c31f6c9452b66336bd)
BibTeX
@misc{dcffbfb14983f9,
title = {A Unified Framework for Wasserstein Convergence of ULMC Methods beyond Log-Concavity: Old and New — arXiv:2609.20713},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.20713},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ffbfb14983f9; sha256 5897074f4e257056bf6361ede6c07072c2ad37b754e943c31f6c9452b66336bd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20713. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
As a fundamental task across computational statistics, scientific computing and machine learning, sampling from high-dimensional probability distributions has received increasing attention in recent years. Numerous sampling algorithms have been proposed, among which underdamped Langevin Monte Carlo (ULMC) methods based on underdamped Langevin dynamics (ULD) have emerged as a class of efficient ones. In this work, we introduce a ``universal" predictor-corrector formulation that bridges Euler-type, UBU-type and randomized schemes through different choices of method parameters. Notably, the ``universal" integrator induces two novel classes of low-cost integrators, termed low-cost randomized integrators (LC-RIs) and low-cost UBU integrators (LC-UBUIs), as well as their exponential-free variants based on polynomial and rational approximations. The resulting new UBU-type and randomized schemes require only one gradient evaluation and two Gaussians per iteration, considerably reducing the number of gradient evaluations or Gaussians per iteration required by existing counterparts. Further, a general framework of long-time error analysis is developed for general discretization schemes in a probability metric. Under certain smoothness and non-log-concavity conditions, we rely on the unified framework to establish non-asymptotic $\mathcal{W}_1$-error bounds of both old and new schemes, revealing convergence rates of order $\mathcal{O}(d^{\frac{1}{2}}h)$ for Euler-type schemes, order $\mathcal{O}(d h^2)$ for UBU-type ones and order $\mathcal{O}(d^{\frac{1}{2}}h^{\frac{3}{2}})$ for randomized ones. In the strongly convex setting, the same non-asymptotic error bounds can be recovered in $\mathcal{W}_2$-distance. Numerical experiments corroborate the theoretical findings.
Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-18 in math.ST).
Categorie arXiv: Numerical Analysis (math.NA) ; Statistics Theory (math.ST).
Pagina del lavoro: https://arxiv.org/abs/2609.20713 — 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 2026-10-10T04:09:43.310Z dalla pagina https://arxiv.org/catchup/math.ST/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).