Optimal parameter choices via precise black-box analysis - Archive ouverte HAL Access content directly
Journal Articles Theoretical Computer Science Year : 2020

Optimal parameter choices via precise black-box analysis


It has been observed that some working principles of evolutionary algorithms, in particular, the influence of the parameters, cannot be understood from results on the asymptotic order of the runtime, but only from more precise results. In this work, we complement the emerging topic of precise runtime analysis with a first precise complexity theoretic result. Our vision is that the interplay between algorithm analysis and complexity theory becomes a fruitful tool also for analyses more precise than asymptotic orders of magnitude. As particular result, we prove that the unary unbiased black-box complexity of the OneMax benchmark function class is nln⁡(n)−cn±o(n) for a constant c which is between 0.2539 and 0.2665. This runtime can be achieved with a simple (1+1)-type algorithm using a fitness-dependent mutation strength. When translated into the fixed-budget perspective, our algorithm finds solutions which are roughly 13% closer to the optimum than those of the best previously known algorithms. To prove our results, we formulate several new versions of the variable drift theorems, which also might be of independent interest.
Fichier principal
Vignette du fichier
Jing TCS old 1807.03403.pdf (677.42 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02175769 , version 1 (15-11-2020)



Benjamin Doerr, Carola Doerr, Jing Yang. Optimal parameter choices via precise black-box analysis. Theoretical Computer Science, 2020, 801, pp.1-34. ⟨10.1016/j.tcs.2019.06.014⟩. ⟨hal-02175769⟩
136 View
55 Download



Gmail Facebook Twitter LinkedIn More