English

Convergence of Simulated Annealing Using Kinetic Langevin Dynamics

Probability 2022-06-14 v1 Numerical Analysis Numerical Analysis Optimization and Control

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.

Keywords

Cite

@article{arxiv.2206.06179,
  title  = {Convergence of Simulated Annealing Using Kinetic Langevin Dynamics},
  author = {Xuedong He and Xiaolu Tan and Ruocheng Wu},
  journal= {arXiv preprint arXiv:2206.06179},
  year   = {2022}
}

Comments

33 pages