Tail Bounds on the Runtime of Categorical Compact Genetic Algorithm
Evolutionary Computation · 2025
DOI: 10.1162/evco_a_00361 ↗Kurz gefasst
Fachartikel in der Zeitschrift Evolutionary Computation, 2025. Verfasst von Ryoki Hamano und 4 weiteren Autor:innen. Beteiligte Einrichtung: CyberAgent, Inc., Tokyo, Japan hamano_ryoki_xa@cyberagent.co.jp. Hauptthemen laut MEDLINE: Algorithms, Models, Genetic. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 30 Literaturangaben.
Abstract (Originalsprache)
The majority of theoretical analyses of evolutionary algorithms in the discrete domain focus on binary optimization algorithms, even though black-box optimization on the categorical domain has many practical applications. In this paper, we consider a probabilistic model-based algorithm using the family of categorical distributions as its underlying distribution and set the sample size as two. We term this specific algorithm the categorical compact genetic algorithm (ccGA). The ccGA can be considered as an extension of the compact genetic algorithm (cGA), which is an efficient binary optimization algorithm. We theoretically analyze the dependency of the number of possible categories K, the number of dimensions D, and the learning rate η on the runtime. We investigate the tail bound of the runtime on two typical linear functions on the categorical domain: categorical OneMax (COM) and KVal. We derive that the runtimes on COM and KVal are O(Dln(DK)/η) and Θ(DlnK/η) with high probability, respectively. Our analysis is a generalization for that of the cGA on the binary domain.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- CyberAgent, Inc., Tokyo, Japan hamano_ryoki_xa@cyberagent.co.jp.
- Yokohama National University, Kanagawa, Japan uchida-kento-fz@ynu.ac.jp.
- Yokohama National University, Kanagawa, Japan shirakawa-shinichi-bg@ynu.ac.jp.
- University of Tsukuba, Ibaraki, Japan; RIKEN Center for Advanced Intelligence Project, Tokyo, Japan morinaga@bbo.cs.tsukuba.ac.jp.
- University of Tsukuba, Ibaraki, Japan; RIKEN Center for Advanced Intelligence Project, Tokyo, Japan akimoto@cs.tsukuba.ac.jp.
ORCID-Profile: Ryoki Hamano, Kento Uchida, Shinichi Shirakawa, Daiki Morinaga, Youhei Akimoto
Zitieren
APA
Hamano, R., Uchida, K., Shirakawa, S., Morinaga, D., & Akimoto, Y. (2025). Tail Bounds on the Runtime of Categorical Compact Genetic Algorithm. Evolutionary Computation. https://doi.org/10.1162/evco_a_00361
Vancouver
Hamano R, Uchida K, Shirakawa S, Morinaga D, Akimoto Y. Tail Bounds on the Runtime of Categorical Compact Genetic Algorithm. Evolutionary Computation. 2025. doi:10.1162/evco_a_00361
BibTeX
@article{Hamano2025,
author = {Hamano, Ryoki and Uchida, Kento and Shirakawa, Shinichi and Morinaga, Daiki and Akimoto, Youhei},
title = {Tail Bounds on the Runtime of Categorical Compact Genetic Algorithm},
journal = {Evolutionary Computation},
year = {2025},
doi = {10.1162/evco_a_00361}
}
EUVIMED