Creative Commons Attribution 3.0 Unported license (CC-BY 3.0)when quoting this document, please refer to the following
DOI: 10.4230/LIPIcs.ICALP.2018.130
URN: urn:nbn:de:0030-drops-91344
URL: https://drops.dagstuhl.de/opus/volltexte/2018/9134/
Kiefer, Stefan
On Computing the Total Variation Distance of Hidden Markov Models
| pdf-format: |
|
Abstract
We prove results on the decidability and complexity of computing the total variation distance (equivalently, the L_1-distance) of hidden Markov models (equivalently, labelled Markov chains). This distance measures the difference between the distributions on words that two hidden Markov models induce. The main results are: (1) it is undecidable whether the distance is greater than a given threshold; (2) approximation is #P-hard and in PSPACE.
BibTeX - Entry
@InProceedings{kiefer:LIPIcs:2018:9134,
author = {Stefan Kiefer},
title = {{On Computing the Total Variation Distance of Hidden Markov Models}},
booktitle = {45th International Colloquium on Automata, Languages, and Programming (ICALP 2018)},
pages = {130:1--130:13},
series = {Leibniz International Proceedings in Informatics (LIPIcs)},
ISBN = {978-3-95977-076-7},
ISSN = {1868-8969},
year = {2018},
volume = {107},
editor = {Ioannis Chatzigiannakis and Christos Kaklamanis and D{\'a}niel Marx and Donald Sannella},
publisher = {Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik},
address = {Dagstuhl, Germany},
URL = {http://drops.dagstuhl.de/opus/volltexte/2018/9134},
URN = {urn:nbn:de:0030-drops-91344},
doi = {10.4230/LIPIcs.ICALP.2018.130},
annote = {Keywords: Labelled Markov Chains, Hidden Markov Models, Distance, Decidability, Complexity}
}
| Keywords: | Labelled Markov Chains, Hidden Markov Models, Distance, Decidability, Complexity | |
| Seminar: | 45th International Colloquium on Automata, Languages, and Programming (ICALP 2018) | |
| Issue date: | 2018 | |
| Date of publication: | 04.07.2018 |
