[1507.05021] Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithm

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status

[1507.05021] Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithm Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Mathematics > Statistics Theory arXiv:1507.05021 (math) [Submitted on 17 Jul 2015 ( v1 ), last revised 19 Dec 2016 (this version, v3)] Title: Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithm Authors: Alain Durmus (LTCI), Eric Moulines (CMAP) View a PDF of the paper titled Non-asymptotic convergence analysis for the Unadjusted Langevin Algorith

related reading

• Gregory Gundersengregorygundersen.com
• Step-by-Step Diffusion: An Elementary Tutorialarxiv.org
• Approximating KL Divergencejoschu.net
• Competing with sampling — Alignment Research Centeralignment.org
• Beyond Gaussian Noise: A Generalized Approach to Likelihood Analysis with Non-Gaussian Noiseiopscience.iop.org
• [2605.15522] Stochastic Non-Smooth Convex Optimization with Unbounded Gradientsarxiv.org
• [2406.08929] Step-by-Step Diffusion: An Elementary Tutorialar5iv.labs.arxiv.org
• ARC progress update: Competing with sampling — LessWronglesswrong.com
• arxiv.org/pdf/2511.08544arxiv.org
• An optimization perspective on log-concave sampling and beyond | Sinho Chewichewisinho.github.io
• Central limit theorem - Wikipediaen.wikipedia.org
• Gärtner-Ellis Theorem and applications.sites.math.northwestern.edu