English

On Non-Elitist Evolutionary Algorithms Optimizing Fitness Functions with a Plateau

Neural and Evolutionary Computing 2020-08-20 v1

Abstract

We consider the expected runtime of non-elitist evolutionary algorithms (EAs), when they are applied to a family of fitness functions with a plateau of second-best fitness in a Hamming ball of radius r around a unique global optimum. On one hand, using the level-based theorems, we obtain polynomial upper bounds on the expected runtime for some modes of non-elitist EA based on unbiased mutation and the bitwise mutation in particular. On the other hand, we show that the EA with fitness proportionate selection is inefficient if the bitwise mutation is used with the standard settings of mutation probability.

Keywords

Cite

@article{arxiv.2004.09491,
  title  = {On Non-Elitist Evolutionary Algorithms Optimizing Fitness Functions with a Plateau},
  author = {Anton V. Eremeev},
  journal= {arXiv preprint arXiv:2004.09491},
  year   = {2020}
}

Comments

14 pages, accepted for proceedings of Mathematical Optimization Theory and Operations Research (MOTOR 2020). arXiv admin note: text overlap with arXiv:1908.08686

R2 v1 2026-06-23T14:58:33.203Z