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

Filip Tronarp, Simo Sarkka

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

109 Downloads (Pure)

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.

Original languageEnglish
Title of host publication44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019; Brighton; United Kingdom; 12-17 May 2019 : Proceedings
PublisherIEEE
Pages5032-5036
Number of pages5
ISBN (Electronic)9781479981311
DOIs
Publication statusPublished - 1 May 2019
MoE publication typeA4 Article in a conference publication
EventIEEE International Conference on Acoustics, Speech, and Signal Processing - Brighton, United Kingdom
Duration: 12 May 201917 May 2019
Conference number: 44

Publication series

NameProceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing
Volume2019-May
ISSN (Print)1520-6149
ISSN (Electronic)2379-190X

Conference

ConferenceIEEE International Conference on Acoustics, Speech, and Signal Processing
Abbreviated titleICASSP
CountryUnited Kingdom
CityBrighton
Period12/05/201917/05/2019

Keywords

  • Bayesian state estimation
  • continuous-discrete filtering
  • non-linear filtering
  • Projection filtering

Fingerprint Dive into the research topics of 'Updates in Bayesian Filtering by Continuous Projections on a Manifold of Densities'. Together they form a unique fingerprint.

Cite this