A Gibbs Sampler for Bayesian Nonparametric State-Space Models

Christos Merkatas, Simo Särkkä

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

101 Downloads (Pure)

Abstract

A common assumption in state space models is that the state and observation noise is Gaussian. However, there are cases where this assumption is violated and is chosen for computational convenience. In this article, we present a state space model whose noise processes are modeled via highly flexible density functions based on Bayesian nonparametric priors with decreasing weights. We are focusing on a system identification problem were the aim is to estimate the parameters and the states of the (possibly) nonlinear dynamical system along with its noise processes using Gibbs sampling. Experiments in simulated data show that the nonparametric model outperforms parametric models especially when the distributions of the noise processes depart from Gaussianity.
Original languageEnglish
Title of host publication2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings
PublisherIEEE
Pages13236-13240
Number of pages5
ISBN (Electronic)979-8-3503-4485-1
DOIs
Publication statusPublished - 18 Mar 2024
MoE publication typeA4 Conference publication
EventIEEE International Conference on Acoustics, Speech and Signal Processing - Seoul, Korea, Republic of, Seoul, Korea, Republic of
Duration: 14 Apr 202419 Apr 2024

Publication series

Name Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing
ISSN (Electronic)2379-190X

Conference

ConferenceIEEE International Conference on Acoustics, Speech and Signal Processing
Abbreviated titleICASSP
Country/TerritoryKorea, Republic of
CitySeoul
Period14/04/202419/04/2024

Keywords

  • Bayesian nonparametrics
  • Gibbs sampling
  • State-space models

Fingerprint

Dive into the research topics of 'A Gibbs Sampler for Bayesian Nonparametric State-Space Models'. Together they form a unique fingerprint.

Cite this