Offspring Population Size Matters when Comparing Evolutionary Algorithms with Self-Adjusting Mutation Rates

Abstract

We analyze the performance of the 2-rate (1+) Evolutionary Algorithm (EA) with self-adjusting mutation rate control, its 3-rate counterpart, and a (1+)~EA variant using multiplicative update rules on the OneMax problem. We compare their efficiency for offspring population sizes ranging up to =3,200 and problem sizes up to n=100,000. Our empirical results show that the ranking of the algorithms is very consistent across all tested dimensions, but strongly depends on the population size. While for small values of the 2-rate EA performs best, the multiplicative updates become superior for starting for some threshold value of between 50 and 100. Interestingly, for population sizes around 50, the (1+)~EA with static mutation rates performs on par with the best of the self-adjusting algorithms. We also consider how the lower bound p_ for the mutation rate influences the efficiency of the algorithms. We observe that for the 2-rate EA and the EA with multiplicative update rules the more generous bound p_=1/n^2 gives better results than p_=1/n when is small. For both algorithms the situation reverses for large~.

Tasks

Reproductions