Learning Centre

Bayesian leave-one-out cross-validation approximations for Gaussian latent variable models

 |  Login

Show simple item record

dc.contributor Aalto-yliopisto fi
dc.contributor Aalto University en
dc.contributor.author Vehtari, Aki
dc.contributor.author Mononen, Tommi
dc.contributor.author Tolvanen, Ville
dc.contributor.author Sivula, Tuomas
dc.contributor.author Winther, Ole
dc.date.accessioned 2018-08-01T13:30:31Z
dc.date.available 2018-08-01T13:30:31Z
dc.date.issued 2016-06-01
dc.identifier.citation Vehtari , A , Mononen , T , Tolvanen , V , Sivula , T & Winther , O 2016 , ' Bayesian leave-one-out cross-validation approximations for Gaussian latent variable models ' , Journal of Machine Learning Research , vol. 17 , pp. 1-38 . < http://www.jmlr.org/papers/v17/14-540.html > en
dc.identifier.issn 1532-4435
dc.identifier.issn 1533-7928
dc.identifier.other PURE UUID: 8869009b-2cb1-4fbe-9baa-dac2780fba66
dc.identifier.other PURE ITEMURL: https://research.aalto.fi/en/publications/8869009b-2cb1-4fbe-9baa-dac2780fba66
dc.identifier.other PURE LINK: http://www.scopus.com/inward/record.url?scp=84988932233&partnerID=8YFLogxK
dc.identifier.other PURE LINK: http://www.jmlr.org/papers/v17/14-540.html
dc.identifier.other PURE FILEURL: https://research.aalto.fi/files/26703470/14_540.pdf
dc.identifier.uri https://aaltodoc.aalto.fi/handle/123456789/32836
dc.description.abstract The future predictive performance of a Bayesian model can be estimated using Bayesian cross-validation. In this article, we consider Gaussian latent variable models where the integration over the latent values is approximated using the Laplace method or expectation propagation (EP). We study the properties of several Bayesian leave-one-out (LOO) cross-validation approximations that in most cases can be computed with a small additional cost after forming the posterior approximation given the full data. Our main objective is to assess the accuracy of the approximative LOO cross-validation estimators. That is, for each method (Laplace and EP) we compare the approximate fast computation with the exact brute force LOO computation. Secondarily, we evaluate the accuracy of the Laplace and EP approximations themselves against a ground truth established through extensive Markov chain Monte Carlo simulation. Our empirical results show that the approach based upon a Gaussian approximation to the LOO marginal distribution (the so-called cavity distribution) gives the most accurate and reliable results among the fast methods. en
dc.format.extent 38
dc.format.extent 1-38
dc.format.mimetype application/pdf
dc.language.iso en en
dc.relation.ispartofseries Journal of Machine Learning Research en
dc.relation.ispartofseries Volume 17 en
dc.rights openAccess en
dc.title Bayesian leave-one-out cross-validation approximations for Gaussian latent variable models en
dc.type A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä fi
dc.description.version Peer reviewed en
dc.contributor.department Department of Computer Science
dc.contributor.department Technical University of Denmark
dc.subject.keyword Expectation propagation
dc.subject.keyword Gaussian latent variable model
dc.subject.keyword Laplace approximation
dc.subject.keyword Leave-one-out cross-validation
dc.subject.keyword Predictive performance
dc.identifier.urn URN:NBN:fi:aalto-201808014237
dc.type.version publishedVersion

Files in this item

Files Size Format View

There are no open access files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search archive

Advanced Search

article-iconSubmit a publication