Feature-based benchmarking of distance-based multi/many-objective optimisation problems: A machine learning perspective - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Feature-based benchmarking of distance-based multi/many-objective optimisation problems: A machine learning perspective

Résumé

We consider the application of machine learning techniques to gain insights into the effect of problem features on algorithm performance, and to automate the task of algorithm selection for distance-based multi- and many-objective optimisation problems. This is the most extensive benchmark study of such problems to date. The problem features can be set directly by the problem generator, and include e.g. the number of variables, objectives, local fronts, and disconnected Pareto sets. Using 945 problem configurations (leading to 28 350 instances) of varying complexity, we find that the problem features and the available optimisation budget (i) affect the considered algorithms (NSGA-II, IBEA, MOEA/D, and random search) in different ways and that (ii) it is possible to recommend a relevant algorithm based on problem features.
Fichier principal
Vignette du fichier
liefooghe_emo2023.pdf (4.23 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04021499 , version 1 (09-03-2023)

Identifiants

Citer

Arnaud Liefooghe, Sébastien Verel, Tinkle Chugh, Jonathan Fieldsend, Richard Allmendinger, et al.. Feature-based benchmarking of distance-based multi/many-objective optimisation problems: A machine learning perspective. EMO 2023 - 12th International Conference on Evolutionary Multi-Criterion Optimization, Mar 2023, Leiden, Netherlands. pp.260-273, ⟨10.1007/978-3-031-27250-9_19⟩. ⟨hal-04021499⟩
63 Consultations
45 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More