CLUSTERING IN BLOCK MARKOV CHAINS

Cited 7 time in webofscience Cited 5 time in scopus
  • Hit : 307
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorSanders, Jaronko
dc.contributor.authorProutiere, Alexandreko
dc.contributor.authorYun, Se-Youngko
dc.date.accessioned2021-01-04T06:50:05Z-
dc.date.available2021-01-04T06:50:05Z-
dc.date.created2020-12-03-
dc.date.created2020-12-03-
dc.date.created2020-12-03-
dc.date.created2020-12-03-
dc.date.issued2020-12-
dc.identifier.citationANNALS OF STATISTICS, v.48, no.6, pp.3488 - 3512-
dc.identifier.issn0090-5364-
dc.identifier.urihttp://hdl.handle.net/10203/279437-
dc.description.abstractThis paper considers cluster detection in Block Markov Chains (BMCs). These Markov chains are characterized by a block structure in their transition matrix. More precisely, the n possible states are divided into a finite number of K groups or clusters, such that states in the same cluster exhibit the same transition rates to other states. One observes a trajectory of the Markov chain, and the objective is to recover, from this observation only, the (initially unknown) clusters. In this paper, we devise a clustering procedure that accurately, efficiently and provably detects the clusters. We first derive a fundamental information-theoretical lower bound on the detection error rate satisfied under any clustering algorithm. This bound identifies the parameters of the BMC, and trajectory lengths, for which it is possible to accurately detect the clusters. We next develop two clustering algorithms that can together accurately recover the cluster structure from the shortest possible trajectories, whenever the parameters allow detection. These algorithms thus reach the fundamental detectability limit, and are optimal in that sense.-
dc.languageEnglish-
dc.publisherINST MATHEMATICAL STATISTICS-
dc.titleCLUSTERING IN BLOCK MARKOV CHAINS-
dc.typeArticle-
dc.identifier.wosid000598369200016-
dc.identifier.scopusid2-s2.0-85099016536-
dc.type.rimsART-
dc.citation.volume48-
dc.citation.issue6-
dc.citation.beginningpage3488-
dc.citation.endingpage3512-
dc.citation.publicationnameANNALS OF STATISTICS-
dc.identifier.doi10.1214/19-AOS1939-
dc.contributor.localauthorYun, Se-Young-
dc.contributor.nonIdAuthorSanders, Jaron-
dc.contributor.nonIdAuthorProutiere, Alexandre-
dc.description.isOpenAccessN-
dc.type.journalArticleArticle-
dc.subject.keywordAuthorClustering-
dc.subject.keywordAuthorMarkov chains-
dc.subject.keywordAuthormixing times-
dc.subject.keywordAuthorcommunity detection-
dc.subject.keywordAuthorchange of measure-
dc.subject.keywordAuthorasymptotic analysis-
dc.subject.keywordAuthorinformation theory-
dc.subject.keywordPlusSEMICIRCLE LAW-
dc.subject.keywordPlusSPECTRUM-
Appears in Collection
AI-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 7 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0