Show simple item record

dc.contributor.authorGavalakis, L
dc.contributor.authorKontoyiannis, Ioannis
dc.date.accessioned2022-01-06T00:30:32Z
dc.date.available2022-01-06T00:30:32Z
dc.date.issued2021-01-01
dc.identifier.issn1083-589X
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/332110
dc.description.abstractA finite form of de Finetti's representation theorem is established using elementary information-theoretic tools: The distribution of the first $k$ random variables in an exchangeable binary vector of length $n\geq k$ is close to a mixture of product distributions. Closeness is measured in terms of the relative entropy and an explicit bound is provided.
dc.publisherInstitute of Mathematical Statistics
dc.rightsAttribution 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectcs.IT
dc.subjectcs.IT
dc.subjectmath.IT
dc.subjectmath.PR
dc.titleAn information-theoretic proof of a finite de finetti theorem
dc.typeArticle
dc.publisher.departmentDepartment of Pure Mathematics And Mathematical Statistics
dc.date.updated2021-12-22T14:04:22Z
prism.issueIdentifiernone
prism.publicationDate2021
prism.publicationNameElectronic Communications in Probability
prism.volume26
dc.identifier.doi10.17863/CAM.79556
rioxxterms.versionofrecord10.1214/21-ECP428
rioxxterms.versionVoR
dc.contributor.orcidKontoyiannis, Ioannis [0000-0001-7242-6375]
dc.identifier.eissn1083-589X
rioxxterms.typeJournal Article/Review
cam.depositDate2021-12-22
pubs.licence-identifierapollo-deposit-licence-2-1
pubs.licence-display-nameApollo Repository Deposit Licence Agreement


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International
Except where otherwise noted, this item's licence is described as Attribution 4.0 International