Show simple item record

dc.contributor.authorRahat, A
dc.contributor.authorChugh, T
dc.contributor.authorFieldsend, J
dc.contributor.authorAllmendinger, R
dc.contributor.authorMiettinen, K
dc.date.accessioned2022-06-21T13:00:52Z
dc.date.issued2022
dc.date.updated2022-06-20T08:56:32Z
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 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_GB
dc.description.sponsorshipEngineering and Physical Sciences Research Council (EPSRC)en_GB
dc.identifier.citationAwaiting citation and DOIen_GB
dc.identifier.grantnumberEP/W01226X/1en_GB
dc.identifier.urihttp://hdl.handle.net/10871/130001
dc.identifierORCID: 0000-0001-5123-8148 (Chugh, Tinkle)
dc.language.isoenen_GB
dc.publisherSpringeren_GB
dc.rights.embargoreasonUnder temporary indefinite embargo pending publication by Springer. 12 month embargo to be applied on publicationen_GB
dc.subjectGauss-Hermiteen_GB
dc.subjectExpected hypervolume improvementen_GB
dc.subjectBayesian optimisationen_GB
dc.subjectMulti-objective optimizationen_GB
dc.subjectCorrelated objectivesen_GB
dc.titleEfficient approximation of expected hypervolume improvement using Gauss-Hermite quadratureen_GB
dc.typeArticleen_GB
dc.date.available2022-06-21T13:00:52Z
exeter.locationDortmund, Germany.
dc.descriptionThis is the author accepted manuscript.en_GB
dc.description16th International Conference on Parallel Problem Solving from Nature (PPSN 2022), 10-14 September 2022, Dortmund, Germany
dc.identifier.journalLecture Notes in Computer Science
dc.rights.urihttp://www.rioxx.net/licenses/all-rights-reserveden_GB
dcterms.dateAccepted2022-06-16
rioxxterms.versionAMen_GB
rioxxterms.licenseref.startdate2022-06-16
rioxxterms.typeJournal Article/Reviewen_GB
refterms.dateFCD2022-06-20T08:56:33Z
refterms.versionFCDAM
refterms.panelBen_GB
pubs.name-of-conferenceParallel Problem Solving from Nature (PPSN)


Files in this item

This item appears in the following Collection(s)

Show simple item record