Hybrid Acquisition Processes in Surrogate-based ...
Document type :
Communication dans un congrès avec actes
Title :
Hybrid Acquisition Processes in Surrogate-based Optimization. Application to Covid-19 Contact Reduction
Author(s) :
Briffoteaux, Guillaume [Auteur]
Université de Mons / University of Mons [UMONS]
Optimisation de grande taille et calcul large échelle [BONUS]
Melab, Nouredine [Auteur]
Optimisation de grande taille et calcul large échelle [BONUS]
Mezmaz, Mohand [Auteur]
Université de Mons / University of Mons [UMONS]
Tuyttens, Daniel [Auteur]
Université de Mons / University of Mons [UMONS]
Université de Mons / University of Mons [UMONS]
Optimisation de grande taille et calcul large échelle [BONUS]
Melab, Nouredine [Auteur]
Optimisation de grande taille et calcul large échelle [BONUS]
Mezmaz, Mohand [Auteur]
Université de Mons / University of Mons [UMONS]
Tuyttens, Daniel [Auteur]
Université de Mons / University of Mons [UMONS]
Conference title :
BIOMA 2022 - International Conference on Bioinspired Optimisation Methods and Their Applications
City :
Maribor
Country :
Slovénie
Start date of the conference :
2022-11-17
HAL domain(s) :
Mathématiques [math]/Optimisation et contrôle [math.OC]
Informatique [cs]/Apprentissage [cs.LG]
Informatique [cs]/Modélisation et simulation
Informatique [cs]/Apprentissage [cs.LG]
Informatique [cs]/Modélisation et simulation
English abstract : [en]
Parallel Surrogate-Assisted Evolutionary Algorithms (P-SAEAs) are based on surrogate-informed reproduction operators to propose new candidates to solve computationally expensive optimization problems. Differently, Parallel ...
Show more >Parallel Surrogate-Assisted Evolutionary Algorithms (P-SAEAs) are based on surrogate-informed reproduction operators to propose new candidates to solve computationally expensive optimization problems. Differently, Parallel Surrogate-Driven Algorithms (P-SDAs) rely on the optimization of a surrogate-informed metric of promisingness to acquire new solutions. The former are promoted to deal with moderately computationally expensive problems while the latter are put forward on very costly problems. This paper investigates the design of hybrid strategies combining the acquisition processes of both P-SAEAs and P-SDAs to retain the best of both categories of methods. The objective is to reach robustness with respect to the computational budgets and parallel scalability.Show less >
Show more >Parallel Surrogate-Assisted Evolutionary Algorithms (P-SAEAs) are based on surrogate-informed reproduction operators to propose new candidates to solve computationally expensive optimization problems. Differently, Parallel Surrogate-Driven Algorithms (P-SDAs) rely on the optimization of a surrogate-informed metric of promisingness to acquire new solutions. The former are promoted to deal with moderately computationally expensive problems while the latter are put forward on very costly problems. This paper investigates the design of hybrid strategies combining the acquisition processes of both P-SAEAs and P-SDAs to retain the best of both categories of methods. The objective is to reach robustness with respect to the computational budgets and parallel scalability.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :
Files
- https://hal.inria.fr/hal-03770742/document
- Open access
- Access the document
- https://hal.inria.fr/hal-03770742/document
- Open access
- Access the document
- https://hal.inria.fr/hal-03770742/document
- Open access
- Access the document
- document
- Open access
- Access the document
- g_briffoteaux_et_al_camera_ready.pdf
- Open access
- Access the document