Title :
A progressive random walk algorithm for sampling continuous fitness landscapes
Author :
Malan, Katherine M. ; Engelbrecht, Andries P.
Author_Institution :
Dept. of Comput. Sci., Univ. of Pretoria, Tshwane, South Africa
Abstract :
A number of fitness landscape analysis approaches are based on random walks through discrete search spaces. Applying these approaches to real-encoded problems requires the notion of a random walk in continuous space. This paper proposes a progressive random walk algorithm and the use of multiple walks to sample neighbourhood structure in continuous multi-dimensional spaces. It is shown that better coverage of a search space is provided by progressive random walks than simple unbiased random walks.
Keywords :
evolutionary computation; random processes; continuous fitness landscape sampling; continuous multidimensional spaces; discrete search spaces; neighbourhood structure sampling; progressive random walk algorithm; search space coverage; Algorithm design and analysis; Atmospheric measurements; Correlation; Hypercubes; Optimization; Search problems; Vectors;
Conference_Titel :
Evolutionary Computation (CEC), 2014 IEEE Congress on
Conference_Location :
Beijing
Print_ISBN :
978-1-4799-6626-4
DOI :
10.1109/CEC.2014.6900576