On averaging the best samples in evolutionary computation [article]

Laurent Meunier, Yann Chevaleyre, Jeremy Rapin, Clément W. Royer, Olivier Teytaud
2020 arXiv   pre-print
Choosing the right selection rate is a long standing issue in evolutionary computation. In the continuous unconstrained case, we prove mathematically that a single parent μ=1 leads to a sub-optimal simple regret in the case of the sphere function. We provide a theoretically-based selection rate μ/λ that leads to better progress rates. With our choice of selection rate, we get a provable regret of order O(λ^-1) which has to be compared with O(λ^-2/d) in the case where μ=1. We complete our study with experiments to confirm our theoretical claims.
arXiv:2004.11685v3 fatcat:o74quqeay5g5dnrz2mxwvm5ypa