File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Entropy rate of continuous-state hidden Markov chains

TitleEntropy rate of continuous-state hidden Markov chains
Authors
KeywordsDiscrete-time
Entropy rates
Finite-state
Gaussian channels
Hidden markov chains
Issue Date2010
PublisherIEEE.
Citation
The IEEE International Symposium on Information Theory (ISIT 2010), Austin, TX., 13-18 June 2010. In Proceedings of ISIT, 2010, p. 1468-1472 How to Cite?
AbstractWe prove that under mild positivity assumptions, the entropy rate of a continuous-state hidden Markov chain, observed when passing a finite-state Markov chain through a discrete-time continuous-output channel, is analytic as a function of the transition probabilities of the underlying Markov chain. We further prove that the entropy rate of a continuous-state hidden Markov chain, observed when passing a mixing finite-type constrained Markov chain through a discrete-time Gaussian channel, is smooth as a function of the transition probabilities of the underlying Markov chain. © 2010 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/126236
ISBN
ISSN
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorHan, Gen_HK
dc.contributor.authorMarcus, Ben_HK
dc.date.accessioned2010-10-31T12:17:18Z-
dc.date.available2010-10-31T12:17:18Z-
dc.date.issued2010en_HK
dc.identifier.citationThe IEEE International Symposium on Information Theory (ISIT 2010), Austin, TX., 13-18 June 2010. In Proceedings of ISIT, 2010, p. 1468-1472en_HK
dc.identifier.isbn978-1-4244-7892-7-
dc.identifier.issn0271-4655-
dc.identifier.urihttp://hdl.handle.net/10722/126236-
dc.description.abstractWe prove that under mild positivity assumptions, the entropy rate of a continuous-state hidden Markov chain, observed when passing a finite-state Markov chain through a discrete-time continuous-output channel, is analytic as a function of the transition probabilities of the underlying Markov chain. We further prove that the entropy rate of a continuous-state hidden Markov chain, observed when passing a mixing finite-type constrained Markov chain through a discrete-time Gaussian channel, is smooth as a function of the transition probabilities of the underlying Markov chain. © 2010 IEEE.en_HK
dc.languageengen_HK
dc.publisherIEEE.-
dc.relation.ispartofProceedings of the IEEE International Symposium on Information Theory, ISIT 2010en_HK
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.rightsIEEE International Symposium on Information Theory. Proceedings. Copyright © IEEE.-
dc.rights©2010 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.-
dc.subjectDiscrete-time-
dc.subjectEntropy rates-
dc.subjectFinite-state-
dc.subjectGaussian channels-
dc.subjectHidden markov chains-
dc.titleEntropy rate of continuous-state hidden Markov chainsen_HK
dc.typeConference_Paperen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=0271-4655&volume=&spage=1468&epage=1472&date=2010&atitle=Entropy+rate+of+continuous-state+hidden+Markov+chains-
dc.identifier.emailHan, G:ghan@hku.hken_HK
dc.identifier.authorityHan, G=rp00702en_HK
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1109/ISIT.2010.5513590en_HK
dc.identifier.scopuseid_2-s2.0-77955697954en_HK
dc.identifier.hkuros173841en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-77955697954&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.spage1468en_HK
dc.identifier.epage1472en_HK
dc.identifier.isiWOS:000287512700296-
dc.description.otherThe IEEE International Symposium on Information Theory (ISIT 2010), Austin, TX., 13-18 June 2010. In Proceedings of ISIT, 2010, p. 1468-1472-
dc.identifier.scopusauthoridHan, G=8640067800en_HK
dc.identifier.scopusauthoridMarcus, B=7102086378en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats