Title :
A partial order approach to noisy fitness functions
Author_Institution :
Dept. of Comput. Sci., Dortmund Univ., Germany
Abstract :
If the fitness values are perturbed by noise then they do not have a definitive total order. As a consequence, traditional selection procedures in evolutionary algorithms may lead to obscure solutions. A potential remedy is as follows: Construct a partial order on the set of noisy fitness values and apply those evolutionary algorithms that have been designed for finding the minimal elements of partially ordered sets. These minimal elements are the only reasonable candidates for the unperturbed true solution. A method for reducing the number of candidate solutions is suggested. From a theoretical point of view it is worth mentioning that all convergence results for evolutionary algorithms with partially ordered fitness sets remain valid for the approach considered here
Keywords :
Gaussian distribution; evolutionary computation; candidate solutions; evolutionary algorithms; minimal elements; noisy fitness functions; noisy fitness values; partial order approach; partially ordered fitness sets; partially ordered sets; selection procedures; Algorithm design and analysis; Computer science; Evolutionary computation; Gaussian distribution; Gaussian noise; Measurement units; Noise measurement; Noise shaping; Shape; Size measurement;
Conference_Titel :
Evolutionary Computation, 2001. Proceedings of the 2001 Congress on
Conference_Location :
Seoul
Print_ISBN :
0-7803-6657-3
DOI :
10.1109/CEC.2001.934407