Analyticity of entropy rates of continuous-state hidden Markov models
The analyticity of the entropy and relative entropy rates of continuous-state hidden Markov models is studied here. Using the analytic continuation principle and the stability properties of the optimal filter, the analyticity of these rates is established for analytically parameterized models. The o...
| Main Authors: | , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
IEEE
2019
|
| _version_ | 1797060154651312128 |
|---|---|
| author | Tadic, V Doucet, A |
| author_facet | Tadic, V Doucet, A |
| author_sort | Tadic, V |
| collection | OXFORD |
| description | The analyticity of the entropy and relative entropy rates of continuous-state hidden Markov models is studied here. Using the analytic continuation principle and the stability properties of the optimal filter, the analyticity of these rates is established for analytically parameterized models. The obtained results hold under relatively mild conditions and cover several useful classes of hidden Markov models. These results are relevant for several theoretically and practically important problems arising in statistical inference, system identification and information theory. |
| first_indexed | 2024-03-06T20:13:25Z |
| format | Journal article |
| id | oxford-uuid:2b599b45-7ced-4927-ac5f-d52aa871023a |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-06T20:13:25Z |
| publishDate | 2019 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:2b599b45-7ced-4927-ac5f-d52aa871023a2022-03-26T12:30:20ZAnalyticity of entropy rates of continuous-state hidden Markov modelsJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:2b599b45-7ced-4927-ac5f-d52aa871023aEnglishSymplectic Elements at OxfordIEEE2019Tadic, VDoucet, AThe analyticity of the entropy and relative entropy rates of continuous-state hidden Markov models is studied here. Using the analytic continuation principle and the stability properties of the optimal filter, the analyticity of these rates is established for analytically parameterized models. The obtained results hold under relatively mild conditions and cover several useful classes of hidden Markov models. These results are relevant for several theoretically and practically important problems arising in statistical inference, system identification and information theory. |
| spellingShingle | Tadic, V Doucet, A Analyticity of entropy rates of continuous-state hidden Markov models |
| title | Analyticity of entropy rates of continuous-state hidden Markov models |
| title_full | Analyticity of entropy rates of continuous-state hidden Markov models |
| title_fullStr | Analyticity of entropy rates of continuous-state hidden Markov models |
| title_full_unstemmed | Analyticity of entropy rates of continuous-state hidden Markov models |
| title_short | Analyticity of entropy rates of continuous-state hidden Markov models |
| title_sort | analyticity of entropy rates of continuous state hidden markov models |
| work_keys_str_mv | AT tadicv analyticityofentropyratesofcontinuousstatehiddenmarkovmodels AT douceta analyticityofentropyratesofcontinuousstatehiddenmarkovmodels |