On convergence of kernel density estimates in particle filtering.

DOI10.14736/KYB-2016-5-0735zbMATH Open1399.65021arXiv1402.3466OpenAlexW2563028007MaRDI QIDQ2956002FDOQ2956002

Authors: David Coufal 

Publication date: 13 January 2017

Published in: Kybernetika (Search for Journal in Brave)

Abstract: The paper deals with kernel density estimates of filtering densities in the particle filter. The convergence of the estimates is investigated by means of Fourier analysis. It is shown that the estimates converge to the theoretical filtering densities in the mean integrated squared error under a certain assumption on the Sobolev character of the filtering densities. A sufficient condition is presented for the persistence of this Sobolev character over time. Both results are extended to partial derivatives of the estimates and filtering densities.

Full work available at URL: https://arxiv.org/abs/1402.3466

Recommendations

• Convergence rates of kernel density estimates in particle filtering
• \(L^p\) \((p>1)\) convergence results for particle filtering
• Particle-kernel estimation of the filter density in state-space models
• A uniform convergence theorem for the numerical solving of the nonlinear filtering problem
• Convergence of the SMC implementation of the PHD filter

zbMATH Keywords

kernel methodsparticle filterFourier analysis

Mathematics Subject Classification ID

Stochastic particle methods (65C35)

Cited In (5)

• Convergence rates of kernel density estimates in particle filtering
• Enhanced consistency of the resampled convolution particle filter
• Particle-kernel estimation of the filter density in state-space models
• Convergence analysis of kernel learning FBSDE filter
• \(L^p\) \((p>1)\) convergence results for particle filtering

This page was built for publication: On convergence of kernel density estimates in particle filtering.

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2956002)