Evolution Control Ensemble Models for ...
Document type :
Communication dans un congrès avec actes
Title :
Evolution Control Ensemble Models for Surrogate-Assisted Evolutionary Algorithms
Author(s) :
Briffoteaux, Guillaume [Auteur]
Université de Mons [UMons]
Optimisation de grande taille et calcul large échelle [BONUS]
Ragonnet, Romain [Auteur]
Monash University [Melbourne]
Mezmaz, Mohand [Auteur]
University of Mons [Belgium] [UMONS]
Melab, Nouredine [Auteur]
Optimisation de grande taille et calcul large échelle [BONUS]
Tuyttens, Daniel [Auteur]
University of Mons [Belgium] [UMONS]
Université de Mons [UMons]
Optimisation de grande taille et calcul large échelle [BONUS]
Ragonnet, Romain [Auteur]
Monash University [Melbourne]
Mezmaz, Mohand [Auteur]
University of Mons [Belgium] [UMONS]
Melab, Nouredine [Auteur]
Optimisation de grande taille et calcul large échelle [BONUS]
Tuyttens, Daniel [Auteur]
University of Mons [Belgium] [UMONS]
Conference title :
High Performance Computing and Simulation 2020
City :
Barcelona
Country :
Espagne
Start date of the conference :
2021-03-27
English keyword(s) :
Surrogate-assisted Optimization
Evolution Control
Evolutionary Algorithm
Bayesian Optimization
Simulation
Massively Parallel Computing
Evolution Control
Evolutionary Algorithm
Bayesian Optimization
Simulation
Massively Parallel Computing
HAL domain(s) :
Informatique [cs]/Recherche opérationnelle [cs.RO]
English abstract : [en]
Finding the trade-off between exploitation and exploration in a Surrogate-Assisted Evolutionary Algorithm is challenging as the focus on the landscape being optimized moves during the search. The balancing is mainly guided ...
Show more >Finding the trade-off between exploitation and exploration in a Surrogate-Assisted Evolutionary Algorithm is challenging as the focus on the landscape being optimized moves during the search. The balancing is mainly guided by Evolution Controls, that decide to simulate, predict or discard newly generated candidate solutions. Combining Evolution Controls in ensembles allows to regulate the degree of exploitation and exploration during the search. In this study, we propose ensemble strategies between multiple Evolution Controls in order to adapt the trade-off for each region scrutinized during the search. Experiments led on benchmark problems and on a real-world application of SARS-CoV-2 Transmission Control reveal that favoring exploration at the beginning of the search and favoring exploitation at the end of the search is beneficial in many cases.Show less >
Show more >Finding the trade-off between exploitation and exploration in a Surrogate-Assisted Evolutionary Algorithm is challenging as the focus on the landscape being optimized moves during the search. The balancing is mainly guided by Evolution Controls, that decide to simulate, predict or discard newly generated candidate solutions. Combining Evolution Controls in ensembles allows to regulate the degree of exploitation and exploration during the search. In this study, we propose ensemble strategies between multiple Evolution Controls in order to adapt the trade-off for each region scrutinized during the search. Experiments led on benchmark problems and on a real-world application of SARS-CoV-2 Transmission Control reveal that favoring exploration at the beginning of the search and favoring exploitation at the end of the search is beneficial in many cases.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :
Files
- https://hal.inria.fr/hal-03332521/document
- Open access
- Access the document
- https://hal.inria.fr/hal-03332521/document
- Open access
- Access the document
- https://hal.inria.fr/hal-03332521/document
- Open access
- Access the document
- document
- Open access
- Access the document
- g_briffoteaux_et_al_HPCS2020.pdf
- Open access
- Access the document