Optimal Sampling For Genetic Algorithms

In many real-world environments, a genetic algorithm designer is often faced with choosing the best tness function from a range of possibilities. Fitness functions diier primarily based upon the speed, accuracy, and cost of a tness evaluation. An important type of tness function is the sampling tness function, which utilizes sampling in order to reduce the noise of tness evaluations. The accuracy and speed of a sampling tness function are directly related to the sample size, which is the number of samples used by the sampling tness function to evaluate an individual chromosome. The optimal sample size denotes the sample size that maximizes the performance of a genetic algorithm within a xed time bound. In this paper, a domain independent lower bound of the optimal sample size is derived, and a sample size pruning method is described.