Discretisation of Langevin diffusion in the weak log-concave case

Marelys Crespo

No 24-1506, TSE Working Papers from Toulouse School of Economics (TSE)

Abstract: The Euler discretisation of Langevin diffusion, also known as Unadjusted Langevin Algorithm, is commonly used in machine learning for sampling from a given distribution µ ∝ e−U . In this paper we investigate a potential U : Rd −→ R which is a weakly convex function and has Lipschitz gradient. We parameterize the weak convexity with the help of the Kurdyka-Lojasiewicz (KL) inequality, that permits to handle a vanishing curvature settings, which is far less restrictive when compared to the simple strongly convex case. We prove that the final horizon of simulation to obtain an ε approximation (in terms of entropy) is of the order ε−1d1+2(1+r)2Poly(log(d), log(ε−1)), where the parameter r is involved in the KL inequality and varies between 0 (strongly convex case) and 1 (limiting Laplace situation).

Keywords: Unadjusted Langevin Algorithm; Entropy; Weak convexity; Rate of convergence (search for similar items in EconPapers)
Date: 2024-02
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.tse-fr.eu/sites/default/files/TSE/docu ... 2024/wp_tse_1506.pdf Full Text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:tse:wpaper:129118

Access Statistics for this paper

More papers in TSE Working Papers from Toulouse School of Economics (TSE) Contact information at EDIRC.
Bibliographic data for series maintained by ().