A Stationary Point Convergence Theory for Evolutionary Algorithms
William E. Hart
Massively Parallel Computing Research Laboratory
P. O. Box 5800
Sandia National Laboratories
Albuquerque, NM 87185-1110
ABSTRACT
This paper defines a class of evolutionary algorithms called
evolutionary pattern search algorithms (EPSAs) and analyzes their
convergence properties. This class of algorithms is closely related to
evolutionary programming, evolution strategie and real-coded genetic
algorithms. EPSAs are self-adapting evolutionary algorithms that
modify the step size of the mutation operator in response to the
success of previous optimization steps. The rule used to adapt the
step size can be used to provide a stationary point convergence theory
for EPSAs on any continuous function. This convergence theory is based
on an extension of the convergence theory for generalized pattern
search methods.