Advanced

Metropolis-hastings improved particle smoother and marginalized models

Nordh, Jerker LU (2015) 23rd European Signal Processing Conference, EUSIPCO 2015 In 2015 23rd European Signal Processing Conference, EUSIPCO 2015 p.973-977
Abstract

This paper combines the Metropolis-Hastings Improved Particle Smoother (MHIPS) with marginalized models. It demonstrates the effectiveness of the combination by looking at two examples; a degenerate model of a double integrator and a fifth order mixed linear/nonlinear Gaussian (MLNLG) model. For the MLNLG model two different methods are compared with the non-marginalized case; the first marginalizes the linear states only during the filtering, the second marginalizes during both the foward filtering and backward smoothing pass. The results demonstrate that marginalization not only improves the overall performance, but also increases the rate of improvement for each iteration of the MHIPS algorithm. It thus reduces the required number of... (More)

This paper combines the Metropolis-Hastings Improved Particle Smoother (MHIPS) with marginalized models. It demonstrates the effectiveness of the combination by looking at two examples; a degenerate model of a double integrator and a fifth order mixed linear/nonlinear Gaussian (MLNLG) model. For the MLNLG model two different methods are compared with the non-marginalized case; the first marginalizes the linear states only during the filtering, the second marginalizes during both the foward filtering and backward smoothing pass. The results demonstrate that marginalization not only improves the overall performance, but also increases the rate of improvement for each iteration of the MHIPS algorithm. It thus reduces the required number of iterations to beat the performance of a Forward-Filter Backward Simulator approach for the same model.

(Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Metropolis-Hasting Improved Particle Smoother, Particle Filter, Particle Smoothing, Rao-Blackwellized smoothing
in
2015 23rd European Signal Processing Conference, EUSIPCO 2015
pages
5 pages
publisher
Institute of Electrical and Electronics Engineers Inc.
conference name
23rd European Signal Processing Conference, EUSIPCO 2015
external identifiers
  • Scopus:84963976820
DOI
10.1109/EUSIPCO.2015.7362528
language
English
LU publication?
yes
id
033b3437-162a-457c-89c2-91649793e176
date added to LUP
2016-09-22 09:32:10
date last changed
2016-10-04 15:19:00
@misc{033b3437-162a-457c-89c2-91649793e176,
  abstract     = {<p>This paper combines the Metropolis-Hastings Improved Particle Smoother (MHIPS) with marginalized models. It demonstrates the effectiveness of the combination by looking at two examples; a degenerate model of a double integrator and a fifth order mixed linear/nonlinear Gaussian (MLNLG) model. For the MLNLG model two different methods are compared with the non-marginalized case; the first marginalizes the linear states only during the filtering, the second marginalizes during both the foward filtering and backward smoothing pass. The results demonstrate that marginalization not only improves the overall performance, but also increases the rate of improvement for each iteration of the MHIPS algorithm. It thus reduces the required number of iterations to beat the performance of a Forward-Filter Backward Simulator approach for the same model.</p>},
  author       = {Nordh, Jerker},
  keyword      = {Metropolis-Hasting Improved Particle Smoother,Particle Filter,Particle Smoothing,Rao-Blackwellized smoothing},
  language     = {eng},
  month        = {12},
  pages        = {973--977},
  publisher    = {ARRAY(0xa54dba0)},
  series       = {2015 23rd European Signal Processing Conference, EUSIPCO 2015},
  title        = {Metropolis-hastings improved particle smoother and marginalized models},
  url          = {http://dx.doi.org/10.1109/EUSIPCO.2015.7362528},
  year         = {2015},
}