Advanced

Efficient Iterated Filtering

Lindström, Erik LU ; Ionides, Edward; Frydendall, Jan and Madsen, Henrik (2012) 16th IFAC Symposium on System Identification In IFAC-PapersOnLine (System Identification, Volume 16) p.1785-1790
Abstract
Parameter estimation in general state space models is not trivial as the likelihood is unknown. We propose a recursive estimator for general state space models, and show that the estimates converge to the true parameters with probability one. The estimates are also asymptotically Cramer-Rao efficient. The proposed estimator is easy to implement as it only relies on non-linear filtering. This makes the framework flexible as it is easy to tune the implementation to achieve computational efficiency. This is done by using the approximation of the score function derived from the theory on Iterative Filtering as a building block within the recursive maximum likelihood estimator.
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
Recursive estimation, maximum likelihood estimator, filtering techniques, stochastic approximation, iterative methods
in
IFAC-PapersOnLine (System Identification, Volume 16)
pages
6 pages
publisher
IFAC & Elsevier Ltd.
conference name
16th IFAC Symposium on System Identification
external identifiers
  • Scopus:84867049749
ISBN
978-3-902823-06-9 (online)
DOI
10.3182/20120711-3-BE-2027.00300
language
English
LU publication?
yes
id
497a6486-6683-4929-b12f-27098379cb04 (old id 3008469)
date added to LUP
2013-01-11 17:17:33
date last changed
2017-02-08 13:39:16
@inproceedings{497a6486-6683-4929-b12f-27098379cb04,
  abstract     = {Parameter estimation in general state space models is not trivial as the likelihood is unknown. We propose a recursive estimator for general state space models, and show that the estimates converge to the true parameters with probability one. The estimates are also asymptotically Cramer-Rao efficient. The proposed estimator is easy to implement as it only relies on non-linear filtering. This makes the framework flexible as it is easy to tune the implementation to achieve computational efficiency. This is done by using the approximation of the score function derived from the theory on Iterative Filtering as a building block within the recursive maximum likelihood estimator.},
  author       = {Lindström, Erik and Ionides, Edward and Frydendall, Jan and Madsen, Henrik},
  booktitle    = {IFAC-PapersOnLine (System Identification, Volume 16)},
  isbn         = {978-3-902823-06-9 (online)},
  keyword      = {Recursive estimation,maximum likelihood estimator,filtering techniques,stochastic approximation,iterative methods},
  language     = {eng},
  pages        = {1785--1790},
  publisher    = {IFAC & Elsevier Ltd.},
  title        = {Efficient Iterated Filtering},
  url          = {http://dx.doi.org/10.3182/20120711-3-BE-2027.00300},
  year         = {2012},
}