Publication detail

A particle stochastic approximation EM algorithm to identify jump Markov nonlinear models

PAPEŽ, M.

Original Title

A particle stochastic approximation EM algorithm to identify jump Markov nonlinear models

Type

conference paper

Language

English

Original Abstract

The identification of static parameters in jump Markov nonlinear models (JMNMs) poses a key challenge in explaining nonlinear and abruptly changing behavior of dynamical systems. This paper introduces a stochastic approximation expectation maximization algorithm to facilitate offline maximum likelihood parameter estimation in JMNMs. The method relies on the construction of a particle Gibbs kernel that takes advantage of the inherent structure of the model to increase the efficiency through Rao-Blackwellization. Numerical examples illustrate that the proposed solution outperforms related approaches.

Keywords

Sequential Monte Carlo; particle Markov chain Monte Carlo; particle Gibbs with ancestor sampling; stochastic approximation; expectation maximization; jump Markov nonlinear models; Rao-Blackwellization

Authors

PAPEŽ, M.

Released

9. 7. 2018

Publisher

International Federation of Automatic Control (IFAC)

ISBN

2405-8963

Periodical

IFAC-PapersOnLine (ELSEVIER)

Year of study

51

Number

15

State

Kingdom of the Netherlands

Pages from

676

Pages to

681

Pages count

6

BibTex

@inproceedings{BUT148841,
  author="Milan {Papež}",
  title="A particle stochastic approximation EM algorithm to identify jump Markov nonlinear models",
  booktitle="Proceedings of the 18th Symposium on System Identification, SYSID 2018",
  year="2018",
  journal="IFAC-PapersOnLine (ELSEVIER)",
  volume="51",
  number="15",
  pages="676--681",
  publisher="International Federation of Automatic Control (IFAC)",
  doi="10.1016/j.ifacol.2018.09.205",
  issn="2405-8963"
}