Näytä suppeat kuvailutiedot

dc.contributor.authorRahat, Alma
dc.contributor.authorChugh, Tinkle
dc.contributor.authorFieldsend, Jonathan
dc.contributor.authorAllmendinger, Richard
dc.contributor.authorMiettinen, Kaisa
dc.contributor.editorRudolph, Günter
dc.contributor.editorKononova, Anna V.
dc.contributor.editorAguirre, Hernán
dc.contributor.editorKerschke, Pascal
dc.contributor.editorOchoa, Gabriela
dc.contributor.editorTušar, Tea
dc.date.accessioned2022-08-22T07:52:39Z
dc.date.available2022-08-22T07:52:39Z
dc.date.issued2022
dc.identifier.citationRahat, A., Chugh, T., Fieldsend, J., Allmendinger, R., & Miettinen, K. (2022). Efficient Approximation of Expected Hypervolume Improvement Using Gauss-Hermite Quadrature. In G. Rudolph, A. V. Kononova, H. Aguirre, P. Kerschke, G. Ochoa, & T. Tušar (Eds.), <i>Parallel Problem Solving from Nature – PPSN XVII : 17th International Conference, PPSN 2022, Dortmund, Germany, September 10–14, 2022, Proceedings, Part II</i> (pp. 90-103). Springer International Publishing. Lecture Notes in Computer Science, 13398. <a href="https://doi.org/10.1007/978-3-031-14714-2_7" target="_blank">https://doi.org/10.1007/978-3-031-14714-2_7</a>
dc.identifier.otherCONVID_151651579
dc.identifier.urihttps://jyx.jyu.fi/handle/123456789/82748
dc.description.abstractMany methods for performing multi-objective optimisation of computationally expensive problems have been proposed recently. Typically, a probabilistic surrogate for each objective is constructed from an initial dataset. The surrogates can then be used to produce predictive densities in the objective space for any solution. Using the predictive densities, we can compute the expected hypervolume improvement (EHVI) due to a solution. Maximising the EHVI, we can locate the most promising solution that may be expensively evaluated next. There are closed-form expressions for computing the EHVI, integrating over the multivariate predictive densities. However, they require partitioning of the objective space, which can be prohibitively expensive for more than three objectives. Furthermore, there are no closed-form expressions for a problem where the predictive densities are dependent, capturing the correlations between objectives. Monte Carlo approximation is used instead in such cases, which is not cheap. Hence, the need to develop new accurate but cheaper approximation methods remains. Here we investigate an alternative approach toward approximating the EHVI using Gauss-Hermite quadrature. We show that it can be an accurate alternative to Monte Carlo for both independent and correlated predictive densities with statistically significant rank correlations for a range of popular test problems.en
dc.format.extent619
dc.format.mimetypeapplication/pdf
dc.language.isoeng
dc.publisherSpringer International Publishing
dc.relation.ispartofParallel Problem Solving from Nature – PPSN XVII : 17th International Conference, PPSN 2022, Dortmund, Germany, September 10–14, 2022, Proceedings, Part II
dc.relation.ispartofseriesLecture Notes in Computer Science
dc.rightsIn Copyright
dc.subject.otherGauss-Hermite
dc.subject.otherexpected hypervolume improvement
dc.subject.otherBayesian optimisation
dc.subject.othermulti-objective optimisation
dc.subject.othercorrelated objectives
dc.titleEfficient Approximation of Expected Hypervolume Improvement Using Gauss-Hermite Quadrature
dc.typeconferenceObject
dc.identifier.urnURN:NBN:fi:jyu-202208224286
dc.contributor.laitosInformaatioteknologian tiedekuntafi
dc.contributor.laitosFaculty of Information Technologyen
dc.contributor.oppiaineMultiobjective Optimization Groupfi
dc.contributor.oppiaineLaskennallinen tiedefi
dc.contributor.oppiainePäätöksen teko monitavoitteisestifi
dc.contributor.oppiaineMultiobjective Optimization Groupen
dc.contributor.oppiaineComputational Scienceen
dc.contributor.oppiaineDecision analytics utilizing causal models and multiobjective optimizationen
dc.type.urihttp://purl.org/eprint/type/ConferencePaper
dc.relation.isbn978-3-031-14714-2
dc.type.coarhttp://purl.org/coar/resource_type/c_5794
dc.description.reviewstatuspeerReviewed
dc.format.pagerange90-103
dc.relation.issn0302-9743
dc.type.versionacceptedVersion
dc.rights.copyright© The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2022
dc.rights.accesslevelopenAccessfi
dc.relation.conferenceInternational Conference on Parallel Problem Solving From Nature
dc.subject.ysobayesilainen menetelmä
dc.subject.ysooptimointi
dc.subject.ysomonitavoiteoptimointi
dc.format.contentfulltext
jyx.subject.urihttp://www.yso.fi/onto/yso/p17803
jyx.subject.urihttp://www.yso.fi/onto/yso/p13477
jyx.subject.urihttp://www.yso.fi/onto/yso/p32016
dc.rights.urlhttp://rightsstatements.org/page/InC/1.0/?language=en
dc.relation.doi10.1007/978-3-031-14714-2_7
jyx.fundinginformationThis work is a part of the thematic research area Decision Analytics Utilizing Causal Models and Multiobjective Optimization (DEMO, jyu.fi/demo) at the University of Jyvaskyla. Dr. Rahat was supported by the Engineering and Physical Research Council [grant number EP/W01226X/1].
dc.type.okmA4


Aineistoon kuuluvat tiedostot

Thumbnail

Aineisto kuuluu seuraaviin kokoelmiin

Näytä suppeat kuvailutiedot

In Copyright
Ellei muuten mainita, aineiston lisenssi on In Copyright