Detail publikace
Benchmarking Seven Multi-objective Optimization Methods from the PlatEMO Platform on the bbob-biobj Test Suite
IBEHEJ, D. KŮDELA, J.
Anglický název
Benchmarking Seven Multi-objective Optimization Methods from the PlatEMO Platform on the bbob-biobj Test Suite
Typ
Stať ve sborníku v databázi WoS či Scopus
Jazyk
en
Originální abstrakt
In this paper, we propose a comparative benchmark of seven multiobjective optimization methods from the PlatEMO platform using the COCO framework for performance assessment and the bi-objective test suite bbob-biobj. A mix of both standard methods and newer techniques from various sources that were implemented in the PlatEMO framework was selected for the comparison. We find that although the selected methods were overall mostly inferior to the top-performing methods from the bbob-biobj data archive, they performed quite well in certain computational budget ranges and specific function subgroups.
Klíčová slova anglicky
Benchmarking; Black-box optimization; Multiobjective methods; PlatEMO platform
Vydáno
2025-08-11
Nakladatel
Association for Computing Machinery, Inc
ISBN
9798400714641
Kniha
Gecco 2025 Companion Proceedings of the 2025 Genetic and Evolutionary Computation Conference Companion
Strany od–do
1883–1890
Počet stran
8
BIBTEX
@inproceedings{BUT200141,
author="David {Ibehej} and Jakub {Kůdela}",
title="Benchmarking Seven Multi-objective Optimization Methods from the PlatEMO Platform on the bbob-biobj Test Suite",
booktitle="Gecco 2025 Companion Proceedings of the 2025 Genetic and Evolutionary Computation Conference Companion",
year="2025",
pages="1883--1890",
publisher="Association for Computing Machinery, Inc",
doi="10.1145/3712255.3734349",
isbn="9798400714641"
}