Traditional Gaussian Process Surrogates in the BBOB Framework

0462909 - ÚI 2017 RIV DE eng C - Conference Paper (international conference)
Repický, J. - Bajer, L. - Holeňa, Martin
Traditional Gaussian Process Surrogates in the BBOB Framework.
Proceedings ITAT 2016: Information Technologies - Applications and Theory. Aachen & Charleston: Technical University & CreateSpace Independent Publishing Platform, 2016 - (Brejová, B.), s. 163-171. CEUR Workshop Proceedings, V-1649. ISBN 978-1-5370-1674-0. ISSN 1613-0073.
[ITAT 2016. Conference on Theory and Practice of Information Technologies /16./. Tatranské Matliare (SK), 15.09.2016-19.09.2016]
R&D Projects: GA MZd(CZ) NV15-33250A
Grant - others:GA MŠk(CZ) LM2015042; SVV(CZ) 260 224
Institutional support: RVO:67985807
Keywords : continuous optimization * objective function evaluation * black-box optimization * Gaussian process * surrogate modelling
Subject RIV: IN - Informatics, Computer Science
http://ceur-ws.org/Vol-1649/163.pdf

Objective function evaluation in continuous optimization tasks is often the operation that dominates the algorithm’s cost. In particular in the case of black-box functions, i.e. when no analytical description is available, and the function is evaluated empirically. In such a situation, utilizing information from a surrogate model of the objective function is a well known technique to accelerate the search. In this paper, we review two traditional approaches to surrogate modelling based on Gaussian processes that we have newly reimplemented in MATLAB: Metamodel Assisted Evolution Strategy using probability of improvement and Gaussian Process Optimization Procedure. In the research reported in this paper, both approaches have been for the first time evaluated on Black-Box Optimization Benchmarking framework (BBOB), a comprehensive benchmark for continuous optimizers.
Permanent Link: http://hdl.handle.net/11104/0262256