Näytä suppeat kuvailutiedot

dc.contributor.authorMazumdar, Atanu
dc.contributor.authorChugh, Tinkle
dc.contributor.authorHakanen, Jussi
dc.contributor.authorMiettinen, Kaisa
dc.date.accessioned2022-10-05T10:12:18Z
dc.date.available2022-10-05T10:12:18Z
dc.date.issued2022
dc.identifier.citationMazumdar, A., Chugh, T., Hakanen, J., & Miettinen, K. (2022). Probabilistic Selection Approaches in Decomposition-based Evolutionary Algorithms for Offline Data-Driven Multiobjective Optimization. <i>IEEE Transactions on Evolutionary Computation</i>, <i>26</i>(5), 1182-1191. <a href="https://doi.org/10.1109/TEVC.2022.3154231" target="_blank">https://doi.org/10.1109/TEVC.2022.3154231</a>
dc.identifier.otherCONVID_117517204
dc.identifier.urihttps://jyx.jyu.fi/handle/123456789/83457
dc.description.abstractIn offline data-driven multiobjective optimization, no new data is available during the optimization process. Approximation models, also known as surrogates, are built using the provided offline data. A multiobjective evolutionary algorithm can be utilized to find solutions by using these surrogates. The accuracy of the approximated solutions depends on the surrogates and approximations typically involve uncertainties. In this paper, we propose probabilistic selection approaches that utilize the uncertainty information of the Kriging models (as surrogates) to improve the solution process in offline data-driven multiobjective optimization. These approaches are designed for decomposition-based multiobjective evolutionary algorithms and can, thus, handle a large number of objectives. The proposed approaches were tested on distance-based visualizable test problems and the DTLZ suite. The proposed approaches produced solutions with a greater hypervolume, and a lower root mean squared error compared to generic approaches and a transfer learning approach that do not use uncertainty information.en
dc.format.mimetypeapplication/pdf
dc.language.isoeng
dc.publisherIEEE
dc.relation.ispartofseriesIEEE Transactions on Evolutionary Computation
dc.rightsIn Copyright
dc.subject.otherKriging
dc.subject.otherGaussian processes
dc.subject.othermetamodelling
dc.subject.othersurrogate
dc.subject.otherkernel density estimation
dc.subject.otherPareto optimality
dc.titleProbabilistic Selection Approaches in Decomposition-based Evolutionary Algorithms for Offline Data-Driven Multiobjective Optimization
dc.typearticle
dc.identifier.urnURN:NBN:fi:jyu-202210054798
dc.contributor.laitosInformaatioteknologian tiedekuntafi
dc.contributor.laitosFaculty of Information Technologyen
dc.contributor.oppiaineTietotekniikkafi
dc.contributor.oppiaineLaskennallinen tiedefi
dc.contributor.oppiaineMultiobjective Optimization Groupfi
dc.contributor.oppiainePäätöksen teko monitavoitteisestifi
dc.contributor.oppiaineMathematical Information Technologyen
dc.contributor.oppiaineComputational Scienceen
dc.contributor.oppiaineMultiobjective Optimization Groupen
dc.contributor.oppiaineDecision analytics utilizing causal models and multiobjective optimizationen
dc.type.urihttp://purl.org/eprint/type/JournalArticle
dc.type.coarhttp://purl.org/coar/resource_type/c_2df8fbb1
dc.description.reviewstatuspeerReviewed
dc.format.pagerange1182-1191
dc.relation.issn1089-778X
dc.relation.numberinseries5
dc.relation.volume26
dc.type.versionacceptedVersion
dc.rights.copyright© 2022 IEEE
dc.rights.accesslevelopenAccessfi
dc.relation.grantnumber311877
dc.subject.ysogaussiset prosessit
dc.subject.ysopareto-tehokkuus
dc.subject.ysomonitavoiteoptimointi
dc.subject.ysokriging-menetelmä
dc.subject.ysoevoluutiolaskenta
dc.format.contentfulltext
jyx.subject.urihttp://www.yso.fi/onto/yso/p38750
jyx.subject.urihttp://www.yso.fi/onto/yso/p28039
jyx.subject.urihttp://www.yso.fi/onto/yso/p32016
jyx.subject.urihttp://www.yso.fi/onto/yso/p3126
jyx.subject.urihttp://www.yso.fi/onto/yso/p28071
dc.rights.urlhttp://rightsstatements.org/page/InC/1.0/?language=en
dc.relation.doi10.1109/TEVC.2022.3154231
dc.relation.funderResearch Council of Finlanden
dc.relation.funderSuomen Akatemiafi
jyx.fundingprogramResearch profiles, AoFen
jyx.fundingprogramProfilointi, SAfi
jyx.fundinginformationThis research was partly supported by the Academy of Finland (grant number 311877) and is related to the thematic research area DEMO (Decision Analytics utilizing Causal Models and Multiobjective Optimization) of the University of Jyväskylä.
dc.type.okmA1


Aineistoon kuuluvat tiedostot

Thumbnail

Aineisto kuuluu seuraaviin kokoelmiin

Näytä suppeat kuvailutiedot

In Copyright
Ellei muuten mainita, aineiston lisenssi on In Copyright