Kumara Sastry

Fitness inheritance in multi-objective optimization

Chen, J.-H., Goldberg, D. E., Ho, S.-Y., Sastry, K. (2002). Proceedings of the Genetic and Evolutionary Computation Conference. 319—326. [Full paper - PDF] [Full paper - PS].

Abstract:

In real-world multi-objective problems, the evaluation of objective functions usually requires a large amount of computation time. Moreover, due to the curse of dimensionality, solving multi-objective problems often requires much longer computation time than solving single-objective problems. Therefore, it is essential to develop efficiency enhancement techniques for solving multi-objective problems. This paper investigates fitness inheritance as a way to speed up multi-objective genetic and evolutionary algorithms. Convergence and population-sizing models are derived and compared with experimental results in two cases: Fitness inheritance without fitness sharing and fitness inheritance with fitness sharing. Results show that the number of function evaluations can be reduced with the use of fitness inheritance.

Comments are closed.