Why Tuning the Control Parameters of Metaheuristic Algorithms Is So Important for Fair Comparison?
Although metaheuristic optimization has become a common practice, new bio-inspired algorithms often suffer from a priori ill reputation. One of the reasons is a common bad practice in metaheuristic proposals. It is essential to pay attention to the quality of conducted experiments, especially when...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Brno University of Technology
2020-12-01
|
Series: | Mendel |
Subjects: | |
Online Access: | https://mendel-journal.org/index.php/mendel/article/view/120 |
id |
doaj-6af023629d444352805ecce128ae1b20 |
---|---|
record_format |
Article |
spelling |
doaj-6af023629d444352805ecce128ae1b202021-07-20T13:20:35ZengBrno University of TechnologyMendel1803-38142571-37012020-12-0126210.13164/mendel.2020.2.009Why Tuning the Control Parameters of Metaheuristic Algorithms Is So Important for Fair Comparison?Anezka Kazikova0Michal Pluhacek1Roman Senkerik2Faculty of Applied Informatics, Tomas Bata University in Zlin, Czech RepublicFaculty of Applied Informatics, Tomas Bata University in Zlin, Czech RepublicFaculty of Applied Informatics, Tomas Bata University in Zlin, Czech Republic Although metaheuristic optimization has become a common practice, new bio-inspired algorithms often suffer from a priori ill reputation. One of the reasons is a common bad practice in metaheuristic proposals. It is essential to pay attention to the quality of conducted experiments, especially when comparing several algorithms among themselves. The comparisons should be fair and unbiased. This paper points to the importance of proper initial parameter configurations of the compared algorithms. We highlight the performance differences with several popular and recommended parameter configurations. Even though the parameter selection was mostly based on comprehensive tuning experiments, the algorithms' performance was surprisingly inconsistent, given various parameter settings. Based on the presented evidence, we conclude that paying attention to the metaheuristic algorithm's parameter tuning should be an integral part of the development and testing processes. https://mendel-journal.org/index.php/mendel/article/view/120Parameter tuningmetaheuristicscomparisonswarm algorithmsconfigurationparticle swarm optimization. |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Anezka Kazikova Michal Pluhacek Roman Senkerik |
spellingShingle |
Anezka Kazikova Michal Pluhacek Roman Senkerik Why Tuning the Control Parameters of Metaheuristic Algorithms Is So Important for Fair Comparison? Mendel Parameter tuning metaheuristics comparison swarm algorithms configuration particle swarm optimization. |
author_facet |
Anezka Kazikova Michal Pluhacek Roman Senkerik |
author_sort |
Anezka Kazikova |
title |
Why Tuning the Control Parameters of Metaheuristic Algorithms Is So Important for Fair Comparison? |
title_short |
Why Tuning the Control Parameters of Metaheuristic Algorithms Is So Important for Fair Comparison? |
title_full |
Why Tuning the Control Parameters of Metaheuristic Algorithms Is So Important for Fair Comparison? |
title_fullStr |
Why Tuning the Control Parameters of Metaheuristic Algorithms Is So Important for Fair Comparison? |
title_full_unstemmed |
Why Tuning the Control Parameters of Metaheuristic Algorithms Is So Important for Fair Comparison? |
title_sort |
why tuning the control parameters of metaheuristic algorithms is so important for fair comparison? |
publisher |
Brno University of Technology |
series |
Mendel |
issn |
1803-3814 2571-3701 |
publishDate |
2020-12-01 |
description |
Although metaheuristic optimization has become a common practice, new bio-inspired algorithms often suffer from a priori ill reputation. One of the reasons is a common bad practice in metaheuristic proposals. It is essential to pay attention to the quality of conducted experiments, especially when comparing several algorithms among themselves. The comparisons should be fair and unbiased. This paper points to the importance of proper initial parameter configurations of the compared algorithms. We highlight the performance differences with several popular and recommended parameter configurations. Even though the parameter selection was mostly based on comprehensive tuning experiments, the algorithms' performance was surprisingly inconsistent, given various parameter settings. Based on the presented evidence, we conclude that paying attention to the metaheuristic algorithm's parameter tuning should be an integral part of the development and testing processes.
|
topic |
Parameter tuning metaheuristics comparison swarm algorithms configuration particle swarm optimization. |
url |
https://mendel-journal.org/index.php/mendel/article/view/120 |
work_keys_str_mv |
AT anezkakazikova whytuningthecontrolparametersofmetaheuristicalgorithmsissoimportantforfaircomparison AT michalpluhacek whytuningthecontrolparametersofmetaheuristicalgorithmsissoimportantforfaircomparison AT romansenkerik whytuningthecontrolparametersofmetaheuristicalgorithmsissoimportantforfaircomparison |
_version_ |
1721293739808260096 |