Limits of performance for the model reduction problem of hidden Markov models

Handle URI:
http://hdl.handle.net/10754/600864
Title:
Limits of performance for the model reduction problem of hidden Markov models
Authors:
Kotsalis, Georgios; Shamma, Jeff S. ( 0000-0001-5638-9551 )
Abstract:
We introduce system theoretic notions of a Hankel operator, and Hankel norm for hidden Markov models. We show how the related Hankel singular values provide lower bounds on the norm of the difference between a hidden Markov model of order n and any lower order approximant of order n̂ < n.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Citation:
Kotsalis, G. and Shamma, J.S., 2015, December. Limits of performance for the model reduction problem of hidden Markov models. In Decision and Control (CDC), 2015 IEEE 54th Annual Conference on (pp. 4674-4679). IEEE.
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Journal:
2015 54th IEEE Conference on Decision and Control (CDC)
Conference/Event name:
2015 54th IEEE Conference on Decision and Control (CDC)
Issue Date:
15-Dec-2015
DOI:
10.1109/CDC.2015.7402948
Type:
Conference Paper
Additional Links:
http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7402948
Appears in Collections:
Conference Papers; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorKotsalis, Georgiosen
dc.contributor.authorShamma, Jeff S.en
dc.date.accessioned2016-03-08T13:26:13Zen
dc.date.available2016-03-08T13:26:13Zen
dc.date.issued2015-12-15en
dc.identifier.citationKotsalis, G. and Shamma, J.S., 2015, December. Limits of performance for the model reduction problem of hidden Markov models. In Decision and Control (CDC), 2015 IEEE 54th Annual Conference on (pp. 4674-4679). IEEE.en
dc.identifier.doi10.1109/CDC.2015.7402948en
dc.identifier.urihttp://hdl.handle.net/10754/600864en
dc.description.abstractWe introduce system theoretic notions of a Hankel operator, and Hankel norm for hidden Markov models. We show how the related Hankel singular values provide lower bounds on the norm of the difference between a hidden Markov model of order n and any lower order approximant of order n̂ < n.en
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.relation.urlhttp://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7402948en
dc.rights(c) 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.en
dc.titleLimits of performance for the model reduction problem of hidden Markov modelsen
dc.typeConference Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journal2015 54th IEEE Conference on Decision and Control (CDC)en
dc.conference.date15-18 Dec. 2015en
dc.conference.name2015 54th IEEE Conference on Decision and Control (CDC)en
dc.conference.locationOsakaen
dc.eprint.versionPost-printen
dc.contributor.institutionSchool of Electrical and Computer Engineering, Georgia Institute of Technologyen
kaust.authorShamma, Jeff S.en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.