Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 6 min ago
PreprintarXiv licencearXiv

Reversible Stratonovich perturbations for accelerating convergence to equilibrium of Langevin dynamics

  • Guillaume Louis
  • Grigorios A. Pavliotis
  • Gilles Vilmart
Open at sourcePDFDOICite

Abstract

In this paper, we study the problem of sampling from a probability distribution using Langevin-type dynamics. We consider overdamped Langevin dynamics perturbed by adding a Stratonovich perturbation that preserves reversibility. We prove an optimal scaling for the Stratonovich perturbation applied to Gaussian target distributions and derive an algorithm to construct such perturbation. Our theoretical results are supplemented by numerical experiments in which we compare our proposed method with nonreversible samplers and overdamped Langevin dynamics. Our numerical experiments demonstrate the efficiency of the approach beyond the quadratic case.

Related

  1. Stratonovich SDEs in High Dimensions: Weak Convergence Approach to Generalized Trivial Coupling
    Yousef Alnafisah, M. A. Sohaly
    MathematicsPeer-reviewedCC BY 4.0General mathematicsCrossref
  2. Accelerating Langevin Dynamics with Weighted Laplacian Flow: Global Well-Posedness and Exponential Convergence
    Ziyue Cai, Weiye Gan, Borui Miao +1
    arXivPreprintarXiv licenceFull textAnalysis & PDEsProbabilityarXiv
  3. An elementary proof of Brémont's theorem on the convergence of equilibrium measures at temperature zero
    Oliver Jenkinson, Mark Pollicott
    arXivPreprintCC BY 4.0Full textDynamical systemsMathematical physicsarXiv
  4. Local stability and rates of convergence to equilibrium for the Nonlinear Renewal Equation; applications to Hawkes processes
    Céline Duval, Eric Luçon
    NonlinearityPeer-reviewedCC BY 4.0Full textDynamical systemsProbabilityHAL
  5. Convergence Guarantees for the Broximal Point Method under Perturbations
    Alina Abdikarimova, Ammar Mahran, Peter Richtárik
    arXivPreprintCC BY 4.0Full textOptimisation & controlarXiv

Cite

BibTeXRIS
BibTeX
@misc{louis2026reversible,
  title = {{Reversible Stratonovich perturbations for accelerating convergence to equilibrium of Langevin dynamics}},
  author = {Guillaume Louis and Grigorios A. Pavliotis and Gilles Vilmart},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.03191},
  eprint = {2610.03191},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.03191},
}
RIS
TY  - UNPB
TI  - Reversible Stratonovich perturbations for accelerating convergence to equilibrium of Langevin dynamics
AU  - Guillaume Louis
AU  - Grigorios A. Pavliotis
AU  - Gilles Vilmart
PY  - 2026
DA  - 2026/10/02
PB  - arXiv
DO  - 10.48550/arxiv.2610.03191
UR  - https://arxiv.org/abs/2610.03191
AB  - In this paper, we study the problem of sampling from a probability distribution using Langevin-type dynamics. We consider overdamped Langevin dynamics perturbed by adding a Stratonovich perturbation that preserves reversibility. We prove an optimal scaling for the Stratonovich perturbation applied to Gaussian target distributions and derive an algorithm to construct such perturbation. Our theoretical results are supplemented by numerical experiments in which we compare our proposed method with nonreversible samplers and overdamped Langevin dynamics. Our numerical experiments demonstrate the efficiency of the approach beyond the quadratic case.
ER  -