Localized probability of improvement for kriging based multi-objective optimization

The paper introduces a new approach to kriging based multi-objective optimization by utilizing a local probability of improvement as the infill sampling criterion and the nearest neighbor check to ensure diversification and uniform distribution of Pareto fronts. The proposed method is computationall...

Full description

Bibliographic Details
Main Authors: Li Yinjiang, Xiao Song, Barba Paolo Di, Rotaru Mihai, Sykulski Jan K.
Format: Article
Language:English
Published: De Gruyter 2017-12-01
Series:Open Physics
Subjects:
Online Access:https://doi.org/10.1515/phys-2017-0117
id doaj-b30986e067414a19b2b0fdca50cb72d5
record_format Article
spelling doaj-b30986e067414a19b2b0fdca50cb72d52021-09-05T13:59:34ZengDe GruyterOpen Physics2391-54712017-12-0115195495810.1515/phys-2017-0117phys-2017-0117Localized probability of improvement for kriging based multi-objective optimizationLi Yinjiang0Xiao Song1Barba Paolo Di2Rotaru Mihai3Sykulski Jan K.4Electronics and Computer Science, University of Southampton, SouthamptonSO17 1BJ, United Kingdom of Great Britain and Northern IrelandElectronics and Computer Science, University of Southampton, SouthamptonSO17 1BJ, United Kingdom of Great Britain and Northern IrelandDepartment of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, ItalyElectronics and Computer Science, University of Southampton, SouthamptonSO17 1BJ, United Kingdom of Great Britain and Northern IrelandElectronics and Computer Science, University of Southampton, SouthamptonSO17 1BJ, United Kingdom of Great Britain and Northern IrelandThe paper introduces a new approach to kriging based multi-objective optimization by utilizing a local probability of improvement as the infill sampling criterion and the nearest neighbor check to ensure diversification and uniform distribution of Pareto fronts. The proposed method is computationally fast and linearly scalable to higher dimensions.https://doi.org/10.1515/phys-2017-0117krigingmulti-objective optimizationpareto frontsurrogate-based optimization89.20.kk85.85.+j85.70.-w87.10.mn
collection DOAJ
language English
format Article
sources DOAJ
author Li Yinjiang
Xiao Song
Barba Paolo Di
Rotaru Mihai
Sykulski Jan K.
spellingShingle Li Yinjiang
Xiao Song
Barba Paolo Di
Rotaru Mihai
Sykulski Jan K.
Localized probability of improvement for kriging based multi-objective optimization
Open Physics
kriging
multi-objective optimization
pareto front
surrogate-based optimization
89.20.kk
85.85.+j
85.70.-w
87.10.mn
author_facet Li Yinjiang
Xiao Song
Barba Paolo Di
Rotaru Mihai
Sykulski Jan K.
author_sort Li Yinjiang
title Localized probability of improvement for kriging based multi-objective optimization
title_short Localized probability of improvement for kriging based multi-objective optimization
title_full Localized probability of improvement for kriging based multi-objective optimization
title_fullStr Localized probability of improvement for kriging based multi-objective optimization
title_full_unstemmed Localized probability of improvement for kriging based multi-objective optimization
title_sort localized probability of improvement for kriging based multi-objective optimization
publisher De Gruyter
series Open Physics
issn 2391-5471
publishDate 2017-12-01
description The paper introduces a new approach to kriging based multi-objective optimization by utilizing a local probability of improvement as the infill sampling criterion and the nearest neighbor check to ensure diversification and uniform distribution of Pareto fronts. The proposed method is computationally fast and linearly scalable to higher dimensions.
topic kriging
multi-objective optimization
pareto front
surrogate-based optimization
89.20.kk
85.85.+j
85.70.-w
87.10.mn
url https://doi.org/10.1515/phys-2017-0117
work_keys_str_mv AT liyinjiang localizedprobabilityofimprovementforkrigingbasedmultiobjectiveoptimization
AT xiaosong localizedprobabilityofimprovementforkrigingbasedmultiobjectiveoptimization
AT barbapaolodi localizedprobabilityofimprovementforkrigingbasedmultiobjectiveoptimization
AT rotarumihai localizedprobabilityofimprovementforkrigingbasedmultiobjectiveoptimization
AT sykulskijank localizedprobabilityofimprovementforkrigingbasedmultiobjectiveoptimization
_version_ 1717813427328516096