Journal article
Analyticity of entropy rates of continuous-state hidden Markov models
- Abstract:
- 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.
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Preview, Accepted manuscript, pdf, 447.2KB, Terms of use)
-
- Publisher copy:
- 10.1109/TIT.2019.2935777
Authors
- Publisher:
- IEEE
- Journal:
- IEEE Transactions on Information Theory More from this journal
- Volume:
- 65
- Issue:
- 12
- Pages:
- 7950-7975
- Publication date:
- 2019-08-16
- Acceptance date:
- 2019-07-29
- DOI:
- ISSN:
-
0018-9448
- Language:
-
English
- Keywords:
- Pubs id:
-
pubs:1036567
- UUID:
-
uuid:2b599b45-7ced-4927-ac5f-d52aa871023a
- Local pid:
-
pubs:1036567
- Source identifiers:
-
1036567
- Deposit date:
-
2019-07-31
- ARK identifier:
Terms of use
- Copyright holder:
- IEEE
- Copyright date:
- 2019
- Rights statement:
- © IEEE 2019.
- Notes:
- This is the accepted manuscript version of the article. The final version will be made available online from IEEE at: https://doi.org/10.1109/TIT.2019.2935777
If you are the owner of this record, you can report an update to it here: Report update to this record