Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Updates in Bayesian Filtering by Continuous Projections on a Manifold of Densities

Tronarp, Filip LU and Särkkä, Simo (2019) IEEE International Conference on Acoustics, Speech, and Signal Processing 2019
Abstract
In this paper, we develop a novel method for approximate continuous-discrete Bayesian filtering. The projection filtering framework is exploited to develop accurate approximations of posterior distributions within parametric classes of probability distributions. This is done by formulating an ordinary differential equation for the posterior distribution that has the prior as initial value and hits the exact posterior after a unit of time. Particular emphasis is put on exponential families, especially the Gaussian family of densities. Experimental results demonstrate the efficacy and flexibility of the method.
Please use this url to cite or link to this publication:
author
and
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) : Print on Demand(PoD) ISBN: - Print on Demand(PoD) ISBN:
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
IEEE International Conference on Acoustics, Speech, and Signal Processing 2019
conference location
Brighton, United Kingdom
conference dates
2019-05-13 - 2019-05-17
external identifiers
  • scopus:85068971999
ISBN
9781479981311
9781479981328
DOI
10.1109/ICASSP.2019.8682279
language
English
LU publication?
no
id
b268f16f-bc93-434b-895b-d34974ad223f
date added to LUP
2023-08-20 23:01:19
date last changed
2024-06-06 13:42:36
@inproceedings{b268f16f-bc93-434b-895b-d34974ad223f,
  abstract     = {{In this paper, we develop a novel method for approximate continuous-discrete Bayesian filtering. The projection filtering framework is exploited to develop accurate approximations of posterior distributions within parametric classes of probability distributions. This is done by formulating an ordinary differential equation for the posterior distribution that has the prior as initial value and hits the exact posterior after a unit of time. Particular emphasis is put on exponential families, especially the Gaussian family of densities. Experimental results demonstrate the efficacy and flexibility of the method.}},
  author       = {{Tronarp, Filip and Särkkä, Simo}},
  booktitle    = {{IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) : Print on Demand(PoD) ISBN:}},
  isbn         = {{9781479981311}},
  language     = {{eng}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  title        = {{Updates in Bayesian Filtering by Continuous Projections on a Manifold of Densities}},
  url          = {{http://dx.doi.org/10.1109/ICASSP.2019.8682279}},
  doi          = {{10.1109/ICASSP.2019.8682279}},
  year         = {{2019}},
}