Publication detail
An Investigation of Structural Bias in Particle Swarm Optimization
IBEHEJ, D. KŮDELA, J.
English title
An Investigation of Structural Bias in Particle Swarm Optimization
Type
Paper in proceedings (conference paper)
Language
en
Original abstract
Many complex optimization problems, for which standard methods do not provide good-enough solutions, require the utilization of efficient metaheuristics. However, it has been found that several metaheuristics suffer from different types of structural biases, that may undermine their performance. In this paper, we investigate one of the most used evolutionary computation methods, the Particle Swarm Optimization algorithm. We utilize a recently developed modular framework for the construction of 123,900 parameterizations of PSO and investigate the effect of the different parameter choices on the identified types of structural bias. We also analyze and discuss the impact of the different types of structural bias found in these parameterizations on their performance on functions from a standard test set.
Keywords in English
Bias; Evolutionary computation; Metaheuristics; Particle Swarm Optimization
Released
2025-04-17
Publisher
Springer Science and Business Media Deutschland GmbH
ISBN
9783031900648
Book
Lecture Notes in Computer Science
Pages from–to
129–144
Pages count
16
BIBTEX
@inproceedings{BUT200145,
author="David {Ibehej} and Jakub {Kůdela}",
title="An Investigation of Structural Bias in Particle Swarm Optimization",
booktitle="Lecture Notes in Computer Science",
year="2025",
journal="Lecture Notes in Computer Science",
pages="129--144",
publisher="Springer Science and Business Media Deutschland GmbH",
doi="10.1007/978-3-031-90065-5\{_}8",
isbn="9783031900648"
}