Stochastic complexity of variational Bayesian hidden Markov models
Variational Bayesian learning was proposed as the approximation method of Bayesian learning. Inspite of efficiency and experimental good performance, their mathematical property has not yet been clarified. In this paper we analyze variational Bayesian hidden Markov models which include the true one...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1119 vol. 2 |
|---|---|
| container_issue | |
| container_start_page | 1114 |
| container_title | |
| container_volume | 2 |
| creator | Hosino, T. Watanabe, K. Watanabe, S. |
| description | Variational Bayesian learning was proposed as the approximation method of Bayesian learning. Inspite of efficiency and experimental good performance, their mathematical property has not yet been clarified. In this paper we analyze variational Bayesian hidden Markov models which include the true one thus the models are non-identifiable. We derive their asymptotic stochastic complexity. It is shown that, in some prior condition, the stochastic complexity is much smaller than those of identifiable models. |
| doi_str_mv | 10.1109/IJCNN.2005.1556009 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_1556009</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1556009</ieee_id><sourcerecordid>1556009</sourcerecordid><originalsourceid>FETCH-LOGICAL-i200t-64c508ebb6212aab7b36e1063d2f0e64d09a102ede0c7e05ff7b6acab788d15d3</originalsourceid><addsrcrecordid>eNo1j8tOwzAURC0eEm3hB2DjH0i4tmMnXtKKQlEpC2Bd3cQ3qiGJqziqyN9TibKaxRyNzjB2KyAVAuz96mWx2aQSQKdCawNgz9hECiOSLIP8nE0hL0BZyAp58V8oq67YNMYvAKmsVRM2fx9CtcM4-IpXod039OOHkYeaH7D3OPjQYcPnOFL02PGdd446_or9dzjwNjhq4jW7rLGJdHPKGftcPn4snpP129Nq8bBO_FFySExWaSioLI0UErHMS2VIgFFO1kAmc2BRgCRHUOUEuq7z0mB1BIvCCe3UjN397Xoi2u5732I_bk_f1S-d2Ey5</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Stochastic complexity of variational Bayesian hidden Markov models</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Hosino, T. ; Watanabe, K. ; Watanabe, S.</creator><creatorcontrib>Hosino, T. ; Watanabe, K. ; Watanabe, S.</creatorcontrib><description>Variational Bayesian learning was proposed as the approximation method of Bayesian learning. Inspite of efficiency and experimental good performance, their mathematical property has not yet been clarified. In this paper we analyze variational Bayesian hidden Markov models which include the true one thus the models are non-identifiable. We derive their asymptotic stochastic complexity. It is shown that, in some prior condition, the stochastic complexity is much smaller than those of identifiable models.</description><identifier>ISSN: 2161-4393</identifier><identifier>ISBN: 0780390482</identifier><identifier>ISBN: 9780780390485</identifier><identifier>EISSN: 2161-4407</identifier><identifier>DOI: 10.1109/IJCNN.2005.1556009</identifier><language>eng</language><publisher>IEEE</publisher><subject>Approximation methods ; Bayesian methods ; Competitive intelligence ; Computational intelligence ; Hidden Markov models ; Natural language processing ; Speech recognition ; Stochastic processes</subject><ispartof>Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005, 2005, Vol.2, p.1114-1119 vol. 2</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/1556009$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2051,4035,4036,27904,54898</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1556009$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Hosino, T.</creatorcontrib><creatorcontrib>Watanabe, K.</creatorcontrib><creatorcontrib>Watanabe, S.</creatorcontrib><title>Stochastic complexity of variational Bayesian hidden Markov models</title><title>Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005</title><addtitle>IJCNN</addtitle><description>Variational Bayesian learning was proposed as the approximation method of Bayesian learning. Inspite of efficiency and experimental good performance, their mathematical property has not yet been clarified. In this paper we analyze variational Bayesian hidden Markov models which include the true one thus the models are non-identifiable. We derive their asymptotic stochastic complexity. It is shown that, in some prior condition, the stochastic complexity is much smaller than those of identifiable models.</description><subject>Approximation methods</subject><subject>Bayesian methods</subject><subject>Competitive intelligence</subject><subject>Computational intelligence</subject><subject>Hidden Markov models</subject><subject>Natural language processing</subject><subject>Speech recognition</subject><subject>Stochastic processes</subject><issn>2161-4393</issn><issn>2161-4407</issn><isbn>0780390482</isbn><isbn>9780780390485</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2005</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNo1j8tOwzAURC0eEm3hB2DjH0i4tmMnXtKKQlEpC2Bd3cQ3qiGJqziqyN9TibKaxRyNzjB2KyAVAuz96mWx2aQSQKdCawNgz9hECiOSLIP8nE0hL0BZyAp58V8oq67YNMYvAKmsVRM2fx9CtcM4-IpXod039OOHkYeaH7D3OPjQYcPnOFL02PGdd446_or9dzjwNjhq4jW7rLGJdHPKGftcPn4snpP129Nq8bBO_FFySExWaSioLI0UErHMS2VIgFFO1kAmc2BRgCRHUOUEuq7z0mB1BIvCCe3UjN397Xoi2u5732I_bk_f1S-d2Ey5</recordid><startdate>2005</startdate><enddate>2005</enddate><creator>Hosino, T.</creator><creator>Watanabe, K.</creator><creator>Watanabe, S.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>2005</creationdate><title>Stochastic complexity of variational Bayesian hidden Markov models</title><author>Hosino, T. ; Watanabe, K. ; Watanabe, S.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i200t-64c508ebb6212aab7b36e1063d2f0e64d09a102ede0c7e05ff7b6acab788d15d3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2005</creationdate><topic>Approximation methods</topic><topic>Bayesian methods</topic><topic>Competitive intelligence</topic><topic>Computational intelligence</topic><topic>Hidden Markov models</topic><topic>Natural language processing</topic><topic>Speech recognition</topic><topic>Stochastic processes</topic><toplevel>online_resources</toplevel><creatorcontrib>Hosino, T.</creatorcontrib><creatorcontrib>Watanabe, K.</creatorcontrib><creatorcontrib>Watanabe, S.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Hosino, T.</au><au>Watanabe, K.</au><au>Watanabe, S.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Stochastic complexity of variational Bayesian hidden Markov models</atitle><btitle>Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005</btitle><stitle>IJCNN</stitle><date>2005</date><risdate>2005</risdate><volume>2</volume><spage>1114</spage><epage>1119 vol. 2</epage><pages>1114-1119 vol. 2</pages><issn>2161-4393</issn><eissn>2161-4407</eissn><isbn>0780390482</isbn><isbn>9780780390485</isbn><abstract>Variational Bayesian learning was proposed as the approximation method of Bayesian learning. Inspite of efficiency and experimental good performance, their mathematical property has not yet been clarified. In this paper we analyze variational Bayesian hidden Markov models which include the true one thus the models are non-identifiable. We derive their asymptotic stochastic complexity. It is shown that, in some prior condition, the stochastic complexity is much smaller than those of identifiable models.</abstract><pub>IEEE</pub><doi>10.1109/IJCNN.2005.1556009</doi></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 2161-4393 |
| ispartof | Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005, 2005, Vol.2, p.1114-1119 vol. 2 |
| issn | 2161-4393 2161-4407 |
| language | eng |
| recordid | cdi_ieee_primary_1556009 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Approximation methods Bayesian methods Competitive intelligence Computational intelligence Hidden Markov models Natural language processing Speech recognition Stochastic processes |
| title | Stochastic complexity of variational Bayesian hidden Markov models |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-24T10%3A12%3A37IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Stochastic%20complexity%20of%20variational%20Bayesian%20hidden%20Markov%20models&rft.btitle=Proceedings.%202005%20IEEE%20International%20Joint%20Conference%20on%20Neural%20Networks,%202005&rft.au=Hosino,%20T.&rft.date=2005&rft.volume=2&rft.spage=1114&rft.epage=1119%20vol.%202&rft.pages=1114-1119%20vol.%202&rft.issn=2161-4393&rft.eissn=2161-4407&rft.isbn=0780390482&rft.isbn_list=9780780390485&rft_id=info:doi/10.1109/IJCNN.2005.1556009&rft_dat=%3Cieee_6IE%3E1556009%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=1556009&rfr_iscdi=true |