Open Access
2024 Convergence of simulated annealing using kinetic Langevin dynamics
Xuedong He, Xiaolu Tan, Ruocheng Wu
Author Affiliations +
Electron. J. Probab. 29: 1-31 (2024). DOI: 10.1214/24-EJP1138

Abstract

We study the simulated annealing algorithm based on the kinetic Langevin dynamics, in order to find the global minimum of a non-convex potential function. For both the continuous time formulation and a discrete time analogue, we obtain the convergence rate results under technical conditions on the potential function, together with an appropriate choice of the cooling schedule and the time discretization parameters.

Citation

Download Citation

Xuedong He. Xiaolu Tan. Ruocheng Wu. "Convergence of simulated annealing using kinetic Langevin dynamics." Electron. J. Probab. 29 1 - 31, 2024. https://doi.org/10.1214/24-EJP1138

Information

Received: 20 November 2023; Accepted: 2 May 2024; Published: 2024
First available in Project Euclid: 11 June 2024

Digital Object Identifier: 10.1214/24-EJP1138

Subjects:
Primary: 46N30 , 60J25 , 60J60

Keywords: convergence rate , discretization , hypocoercivity , kinetic Langevin dynamics , simulated annealing

Vol.29 • 2024
Back to Top