Observations in applying Bayesian versus evolutionary approaches and their hybrids in parallel time-constrained optimization

Parallel Surrogate-Based Optimization (PSBO) is an efficient approach to deal with black-box time-consuming objective functions. According to the available computational budget to solve a given problem, three classes of algorithms are investigated and opposed in this paper: Bayesian Optimization Alg...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Engineering applications of artificial intelligence Ročník 137; s. 109075
Hlavní autoři: Gobert, Maxime, Briffoteaux, Guillaume, Gmys, Jan, Melab, Nouredine, Tuyttens, Daniel
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.11.2024
Elsevier
Témata:
Bayesian optimization
Computer Science
Evolutionary algorithms
Operations Research
Parallel computing
Surrogate-based optimization
Surrogate-based optimization
Parallel computing
68W10
Evolutionary algorithms
Bayesian optimization
65Y05
46N10
g74P99
ISSN:0952-1976
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Parallel Surrogate-Based Optimization (PSBO) is an efficient approach to deal with black-box time-consuming objective functions. According to the available computational budget to solve a given problem, three classes of algorithms are investigated and opposed in this paper: Bayesian Optimization Algorithms (BOAs), Surrogate-Assisted Evolutionary Algorithms (SAEAs) and Surrogate-free Evolutionary Algorithms (EAs). A large set of benchmark functions and engineering applications are considered with various computational budgets. In this paper, we come up with guidelines for the choice between the three categories. According to the computational expensiveness of the objective functions and the number of processing cores, we identify a threshold from which SAEAs should be preferred to BOAs. Based on this threshold, we derive a new hybrid Bayesian/Evolutionary algorithm that allows one to tackle a wide range of problems without prior knowledge of their characteristics.
ISSN:0952-1976
DOI:10.1016/j.engappai.2024.109075