Please use this identifier to cite or link to this item: http://dx.doi.org/10.18419/opus-12396
Full metadata record
DC FieldValueLanguage
dc.contributor.authorKuchelmeister, Manuel-
dc.date.accessioned2022-09-27T07:08:51Z-
dc.date.available2022-09-27T07:08:51Z-
dc.date.issued2022de
dc.identifier.other181773105X-
dc.identifier.urihttp://nbn-resolving.de/urn:nbn:de:bsz:93-opus-ds-124155de
dc.identifier.urihttp://elib.uni-stuttgart.de/handle/11682/12415-
dc.identifier.urihttp://dx.doi.org/10.18419/opus-12396-
dc.description.abstractThe computational optimization and exploration of materials is a challenging task, due to the high dimensionality of the search space and the high cost of accurate quantum mechanical calculations. To reduce the number of costly calculations, the Bayesian Optimization Structure Search (BOSS) has been developed. BOSS combines sample-efficient active learning with Gaussian process regression. This work introduces several multi-fidelity approaches that can reduce the number of costly, accurate calculations even further by incorporating information from inexpensive but less accurate calculations. Using the intrinsic model of coregionalization, BOSS samples data from multiple atomistic calculations based on quantum chemistry (Gaussian16, using CCSD(T)), density-functional theory (FHI-aims, using a PBE-exchange correlation functional) and force fields (AMBER18). Multi-fidelity BOSS samples both, lower and higher-fidelity calculations, while maintaining CCSD(T) accuracy for the global minimum inference. We tested our new multi-fidelity approaches on a 4D alanine conformer search. There, multi-fidelity BOSS has reduced the computational cost, measured in CPU hours, by up to 90%. We found that the efficiency of the approaches depends mostly on the correlation and the computational cost difference between the fidelities. These tests serve as a benchmark for the great potential that multi-fidelity learning can have to reduce the cost of expensive structure-search problems.en
dc.language.isoende
dc.rightsinfo:eu-repo/semantics/openAccessde
dc.subject.ddc530de
dc.titleMulti-fidelity Bayesian machine learning for global optimizationen
dc.typemasterThesisde
ubs.fakultaetMathematik und Physikde
ubs.institutInstitut für Theoretische Physik Ide
ubs.publikation.seiten99de
ubs.publikation.typAbschlussarbeit (Master)de
Appears in Collections:08 Fakultät Mathematik und Physik

Files in This Item:
File Description SizeFormat 
msc_thesis.pdf2,05 MBAdobe PDFView/Open


Items in OPUS are protected by copyright, with all rights reserved, unless otherwise indicated.