Ziv-Merhav estimation for hidden-Markov processes
| Autor: | Barnfield, Nicholas, Grondin, Raphaël, Pozzoli, Gaia, Raquépas, Renaud |
|---|---|
| Rok vydání: | 2024 |
| Předmět: | |
| Zdroj: | IEEE International Symposium on Information Theory 2024, 3606-3611 |
| Druh dokumentu: | Working Paper |
| DOI: | 10.1109/ISIT57864.2024.10619304 |
| Popis: | We present a proof of strong consistency of a Ziv-Merhav-type estimator of the cross entropy rate for pairs of hidden-Markov processes. Our proof strategy has two novel aspects: the focus on decoupling properties of the laws and the use of tools from the thermodynamic formalism. Comment: Short note prepared for the IEEE International Symposium on Information Theory 2024 on a special case of arXiv:2312.02098 |
| Databáze: | arXiv |
| Externí odkaz: |
|