A surrogate-based cooperative optimization framework for computationally expensive black-box problems

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: A surrogate-based cooperative optimization framework for computationally expensive black-box problems
Συγγραφείς: García García, José Carlos, García Ródenas, Ricardo, Codina Sancho, Esteve
Συνεισφορές: Universitat Politècnica de Catalunya. Departament d'Estadística i Investigació Operativa, Universitat Politècnica de Catalunya. IMP - Information Modeling and Processing
Πηγή: UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Στοιχεία εκδότη: Springer Science and Business Media LLC, 2020.
Έτος έκδοσης: 2020
Θεματικοί όροι: Classificació AMS::68 Computer science::68W Algorithms, 68 Computer science::68W Algorithms [Classificació AMS], Àrees temàtiques de la UPC::Matemàtiques i estadística, Radial basis functions, Black-box function, Expected improvement, Cooperative optimization, 0211 other engineering and technologies, Parallel surrogate-based optimization, Matemàtiques i estadística [Àrees temàtiques de la UPC], 02 engineering and technology
Περιγραφή: The final publication is available at link.springer.com Most parallel surrogate-based optimization algorithms focus only on the mechanisms for generating multiple updating points in each cycle, and rather less attention has been paid to producing them through the cooperation of several algorithms. For this purpose, a surrogate-based cooperative optimization framework is here proposed. Firstly, a class of parallel surrogate-based optimization algorithms is developed, based on the idea of viewing the infill sampling criterion as a bi-objective optimization problem. Each algorithm of this class is called a Sequential Multipoint Infill Sampling Algorithm (SMISA) and is the combination resulting from choosing a surrogate model, an exploitation measure, an exploration measure and a multi-objective optimization approach to its solution. SMISAs are the basic algorithms on which collaboration mechanisms are established. Many SMISAs can be defined, and the focus has been on scalar approaches for bi-objective problems such as the e-constrained method, revisiting the Parallel Constrained Optimization using Response Surfaces (CORS-RBF) method and the Efficient Global Optimization with Pseudo Expected Improvement (EGO-PEI) algorithm as instances of SMISAs. In addition, a parallel version of the Lower Confidence Bound-based (LCB) algorithm is given as a member within the SMISA class. Secondly, we propose a cooperative optimization framework between the SMISAs. The cooperation between SMISAs occurs in two ways: (1) they share solutions and their objective function values to update their surrogate models and (2) they use the sampled points obtained from different SMISAs to guide their own search process. Some convergence results for this cooperative framework are given under weak conditions. A numerical comparison between EGO-PEI, Parallel CORS-RBF and a cooperative method using both, named CPEI, shows that CPEI improves the performance of the baseline algorithms. The numerical results were derived from 17 analytic tests and they show the reduction of wall-clock time with respect to the increase in the number of processors.
Τύπος εγγράφου: Article
Περιγραφή αρχείου: application/pdf
Γλώσσα: English
ISSN: 1573-2924
1389-4420
DOI: 10.1007/s11081-020-09526-7
Σύνδεσμος πρόσβασης: https://link.springer.com/content/pdf/10.1007/s11081-020-09526-7.pdf
http://hdl.handle.net/2117/345025
https://link.springer.com/article/10.1007/s11081-020-09526-7
https://upcommons.upc.edu/handle/2117/345025
https://link.springer.com/content/pdf/10.1007/s11081-020-09526-7.pdf
https://upcommons.upc.edu/bitstream/2117/345025/1/localQual.pdf
https://www.scilit.net/article/8557c51bd762291f52bc446d6b7b7f65
https://hdl.handle.net/2117/345025
https://doi.org/10.1007/s11081-020-09526-7
Rights: CC BY
Αριθμός Καταχώρησης: edsair.doi.dedup.....3faa36436978d44f44c2b515a26fb65d
Βάση Δεδομένων: OpenAIRE
Περιγραφή
ISSN:15732924
13894420
DOI:10.1007/s11081-020-09526-7