Student-t process quadratures for filtering of non-linear systems with heavy-tailed noise

Jakub Prüher, Filip Tronarp, Toni Karvonen, Simo Särkkä, Ondrej Straka

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

9 Citations (Scopus)
132 Downloads (Pure)

Abstract

The aim of this article is to design a moment transformation for Student-t distributed random variables, which is able to account for the error in the numerically computed mean. We employ Student-t process quadrature, an instance of Bayesian quadrature, which allows us to treat the integral itself as a random variable whose variance provides information about the incurred integration error. Advantage of the Student-t process quadrature over the traditional Gaussian process quadrature, is that the integral variance depends also on the function values, allowing for a more robust modelling of the integration error. The moment transform is applied in nonlinear sigma-point filtering and evaluated on two numerical examples, where it is shown to outperform the state-of-the-art moment transforms.
Original languageEnglish
Title of host publication20th International Conference on Information Fusion, Fusion 2017 - Proceedings
PublisherIEEE
Pages875-882
Number of pages8
ISBN (Electronic)978-0-9964-5270-0
DOIs
Publication statusPublished - Jul 2017
MoE publication typeA4 Article in a conference publication
EventInternational Conference on Information Fusion - Xian, China, Xian, China
Duration: 10 Jul 201713 Jul 2017
Conference number: 20
http://www.fusion2017.org/

Conference

ConferenceInternational Conference on Information Fusion
Abbreviated titleFUSION
CountryChina
CityXian
Period10/07/201713/07/2017
Internet address

Fingerprint Dive into the research topics of 'Student-t process quadratures for filtering of non-linear systems with heavy-tailed noise'. Together they form a unique fingerprint.

Cite this