Improving the Model Guided Sampling Optimization by Model Search and Slice Sampling

0396832 - ÚI 2014 RIV US eng C - Konferenční příspěvek (zahraniční konf.)
Bajer, Lukáš - Holeňa, Martin - Charypar, V.
Improving the Model Guided Sampling Optimization by Model Search and Slice Sampling.
ITAT 2013: Information Technologies - Applications and Theory Workshops, Posters, and Tutorials. North Charleston: CreateSpace Independent Publishing Platform, 2013 - (Vinař, T.; Holeňa, M.; Lexa, M.; Peška, L.; Vojtáš, P.), s. 86-91. ISBN 978-1-4909-5208-6.
[ITAT 2013. Conference on Theory and Practice of Information Technologies. Donovaly (SK), 11.09.2013-15.09.2013]
Grant CEP: GA ČR GAP202/11/1368; GA ČR GA13-17187S
Grant ostatní: GA UK(CZ) 278511/2011; GA CTU(CZ) SGS12/196/OHK3/3T/14
Institucionální podpora: RVO:67985807
Klíčová slova: black-box optimization * evolutionary optimization * EGO * Gaussian process * slice sampling
Kód oboru RIV: IN - Informatika

Model Guided Sampling Optimization (MGSO) was recently proposed as an alternative for Jones’ Krigingbased EGO algorithm for optimization of expensive blackbox functions. Instead of maximizing a chosen criterion (e.g., expected improvement), MGSO samples probability of improvement of the Gaussian process model forming multiple candidates – a whole population of suggested solutions. This paper further develops this algorithm using slice sampling method and continuous local optimization of the Gaussian process model.
Trvalý link: http://hdl.handle.net/11104/0224521