Conference item icon

Conference item

Equivalence of hidden Markov models with continuous observations

Abstract:
We consider Hidden Markov Models that emit sequences of observations that are drawn from continuous distributions. For example, such a model may emit a sequence of numbers, each of which is drawn from a uniform distribution, but the support of the uniform distribution depends on the state of the Hidden Markov Model. Such models generalise the more common version where each observation is drawn from a finite alphabet. We prove that one can determine in polynomial time whether two Hidden Markov Models with continuous observations are equivalent.
Publication status:
Accepted
Peer review status:
Peer reviewed

Actions


Access Document


Files:

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Author, Depositor
Publisher:
Schloss Dagstuhl - Leibniz-Zentrum für Informatik Publisher's website
Journal:
Leibniz International Proceedings in Informatics Journal website
Acceptance date:
2020-09-14
Event title:
40th IARCS Annual Conference on FSTTCS 2020
Event location:
Online
Event website:
https://www.fsttcs.org.in/
Event start date:
2020-12-14T00:00:00Z
Event end date:
2020-12-18T00:00:00Z
Pubs id:
1135756
Local pid:
pubs:1135756

Metrics



If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP