Equivalence of hidden Markov models with continuous observations
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 Hid...
| Main Authors: | , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
Schloss Dagstuhl - Leibniz-Zentrum für Informatik
2020
|
| _version_ | 1826259477728329728 |
|---|---|
| author | Darwin, O Kiefer, SM |
| author_facet | Darwin, O Kiefer, SM |
| author_sort | Darwin, O |
| collection | OXFORD |
| description | 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. |
| first_indexed | 2024-03-06T18:50:30Z |
| format | Conference item |
| id | oxford-uuid:100d8e4f-67a8-4836-95da-8c0fe043e369 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-06T18:50:30Z |
| publishDate | 2020 |
| publisher | Schloss Dagstuhl - Leibniz-Zentrum für Informatik |
| record_format | dspace |
| spelling | oxford-uuid:100d8e4f-67a8-4836-95da-8c0fe043e3692022-03-26T09:54:25ZEquivalence of hidden Markov models with continuous observationsConference itemhttp://purl.org/coar/resource_type/c_c94fuuid:100d8e4f-67a8-4836-95da-8c0fe043e369EnglishSymplectic ElementsSchloss Dagstuhl - Leibniz-Zentrum für Informatik2020Darwin, OKiefer, SMWe 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. |
| spellingShingle | Darwin, O Kiefer, SM Equivalence of hidden Markov models with continuous observations |
| title | Equivalence of hidden Markov models with continuous observations |
| title_full | Equivalence of hidden Markov models with continuous observations |
| title_fullStr | Equivalence of hidden Markov models with continuous observations |
| title_full_unstemmed | Equivalence of hidden Markov models with continuous observations |
| title_short | Equivalence of hidden Markov models with continuous observations |
| title_sort | equivalence of hidden markov models with continuous observations |
| work_keys_str_mv | AT darwino equivalenceofhiddenmarkovmodelswithcontinuousobservations AT kiefersm equivalenceofhiddenmarkovmodelswithcontinuousobservations |