Paper Info
Title
An analysis of parameter sensitivities of preference-inspired co-evolutionary algorithms
Abstract
Many-objective optimisation problems remain challenging for many state-of-the-art multi-objective evolutionary algorithms. Preference-inspired co-evolutionary algorithms PICEAs which co-evolve the usual population of candidate solutions with a family of decision-maker preferences during the search have been demonstrated to be effective on such problems. However, it is unknown whether PICEAs are robust with respect to the parameter settings. This study aims to address this question. First, a global sensitivity analysis method – the Sobol’ variance decomposition method – is employed to determine the relative importance of the parameters controlling the performance of PICEAs. Experimental results show that the performance of PICEAs is controlled for the most part by the number of function evaluations. Next, we investigate the effect of key parameters identified from the Sobol’ test and the genetic operators employed in PICEAs. Experimental results show improved performance of the PICEAs as more preferences are co-evolved. Additionally, some suggestions for genetic operator settings are provided for non-expert users.
Year
DOI
Venue
2015
10.1080/00207721.2015.1008600
International Journal of Systems Science
Keywords
Field
DocType
evolutionary algorithm, multi-objective optimisation, Sobol, sensitivity, preferences
Variance decomposition of forecast errors,Population,Genetic operator,Mathematical optimization,Evolutionary algorithm,Operator (computer programming),Global sensitivity analysis,Mathematics,Sobol sequence
Journal
Volume
Issue
ISSN
46
13
0020-7721
Citations 
PageRank 
References 
7
0.43
29
Authors
4
Name
Order
Citations
PageRank
Rui Wang153833.29
Maszatul M. Mansor270.43
Robin C. Purshouse362830.00
Peter J. Fleming43023475.23