Fitness modeling with markov networks

Abstract

Fitness modelling has received growing interest from the evolutionary computation community in recent years. With a fitness model, one can improve evolutionary algorithm efficiency by directly sampling new solutions, developing hybrid guided evolutionary operators or using the model as a surrogate for an expensive fitness function. This paper addresses several issues on fitness modelling of discrete functions, in particular how modelling quality and efficiency can be improved. We define the Markov network fitness model (MFM) in terms of Walsh functions. We explore the relationship between the MFM and fitness in a number of discrete problems, showing how the parameters of the fitness model can identify qualitative features of the fitness function. We define the fitness prediction correlation, a metric to measure fitness modelling capability of local and global fitness models. We use this metric to investigate the effects of population size and selection on the trade-off between model quality and complexity for the MFM.