The Performance of Genetic Algorithms on Walsh Polynomials: Some Anomalous Results and Their Explanation

In this paper we discuss a number of seemingly anomalous results reported by Tanese concerning the performance of the genetic algorithm (GA) on a subclass of Walsh polynomials. Tanese found that the GA optimized these functions poorly and that a partitioning of a single large population into a number of smaller independent populations seemed to improve performance. We reexamine these results experimentally and theoretically, and propose and evaluate some explanations. In addition, we examine the question of what are reasonable and appropriate ways to measure the performance of genetic algorithms. 11 refs., 1 tab.