Publication detail

Approximate Bayesian inference methods for mixture filtering with known model of switching

PAPEŽ, M.

Original Title

Approximate Bayesian inference methods for mixture filtering with known model of switching

English Title

Approximate Bayesian inference methods for mixture filtering with known model of switching

Type

conference paper

Language

en

Original Abstract

Bayesian inference has proven itself to be a practically useful tool for many scientific fields. The exact Bayesian inference is, however, possible in only a narrow class of probabilistic models enjoying the conjugacy principle. It is rather typical that the principle does not hold, and therefore the approximate Bayesian inference methods are taken into account. The present paper compares some of these techniques on a mixture filtering problem. The methods are presented in a generic way, considering that the mixture components are members of the exponential family of probability distributions and that the Markov model of switching between the mixture components is known. A particular instance of the methods is given for a mixture of normal linear state space models, and experiments evaluating the estimation precision and computational time are performed.

English abstract

Bayesian inference has proven itself to be a practically useful tool for many scientific fields. The exact Bayesian inference is, however, possible in only a narrow class of probabilistic models enjoying the conjugacy principle. It is rather typical that the principle does not hold, and therefore the approximate Bayesian inference methods are taken into account. The present paper compares some of these techniques on a mixture filtering problem. The methods are presented in a generic way, considering that the mixture components are members of the exponential family of probability distributions and that the Markov model of switching between the mixture components is known. A particular instance of the methods is given for a mixture of normal linear state space models, and experiments evaluating the estimation precision and computational time are performed.

Keywords

Approximate Bayesian inference methods, decision-making theory, probabilistic mixtures, computational statistics

Released

30.06.2016

Publisher

Institute of Electrical and Electronics Engineers

Location

Tatranska Lomnica

ISBN

978-1-4673-8606-7

Book

Proceedings of the 17th International Carpathian Control Conference, ICCC 2016

Pages from

545

Pages to

551

Pages count

7

URL

Documents

BibTex


@inproceedings{BUT127522,
  author="Milan {Papež}",
  title="Approximate Bayesian inference methods for mixture filtering with known model of switching",
  annote="Bayesian inference has proven itself to be a practically useful tool for many scientific fields. The exact Bayesian inference is, however, possible in only a narrow class of probabilistic models enjoying the conjugacy principle. It is rather typical that the principle does not hold, and therefore the approximate Bayesian inference methods are taken into account. The present paper compares some of these techniques on a mixture filtering problem. The methods are presented in a generic way, considering that the mixture components are members of the exponential family of probability distributions and that the Markov model of switching between the mixture components is known. A particular instance of the methods is given for a mixture of normal linear state space models, and experiments evaluating the estimation precision and computational time are performed.",
  address="Institute of Electrical and Electronics Engineers",
  booktitle="Proceedings of the 17th International Carpathian Control Conference, ICCC 2016",
  chapter="127522",
  doi="10.1109/CarpathianCC.2016.7501157",
  howpublished="online",
  institution="Institute of Electrical and Electronics Engineers",
  year="2016",
  month="june",
  pages="545--551",
  publisher="Institute of Electrical and Electronics Engineers",
  type="conference paper"
}