Annealing schedule from population dynamics
Statistical Mechanics
2009-10-31 v1 adap-org
Adaptation and Self-Organizing Systems
Populations and Evolution
Abstract
We introduce a dynamical annealing schedule for population-based optimization algorithms with mutation. On the basis of a statistical mechanics formulation of the population dynamics, the mutation rate adapts to a value maximizing expected rewards at each time step. Thereby, the mutation rate is eliminated as a free parameter from the algorithm.
Cite
@article{arxiv.cond-mat/9903077,
title = {Annealing schedule from population dynamics},
author = {Stefan Bornholdt},
journal= {arXiv preprint arXiv:cond-mat/9903077},
year = {2009}
}
Comments
6 pages RevTeX, 4 figures PostScript; to be published in Phys. Rev. E