A globally convergent matricial algorithm for multivariate spectral estimation

Simple item page
dc.creatorRamponi, Federico
dc.creatorFerrante, Augusto
dc.creatorPavon, Michele
dc.date2008-09-29
dc.date.accessioned2026-07-07T10:06:14Z
dc.date.available2026-07-07T10:06:14Z
dc.descriptionIn this paper, we first describe a matricial Newton-type algorithm designed to solve the multivariable spectrum approximation problem. We then prove its global convergence. Finally, we apply this approximation procedure to multivariate spectral estimation, and test its effectiveness through simulation. Simulation shows that, in the case of short observation records, this method may provide a valid alternative to standard multivariable identification techniques such as MATLAB's PEM and MATLAB's N4SID.
dc.identifierhttps://arxiv.org/abs/0809.5024
dc.identifierhttp://arxiv.org/abs/0809.5024
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/170255
dc.subjectOptimization and Control
dc.titleA globally convergent matricial algorithm for multivariate spectral estimation
dc.typetext

Files

Collections

arXiv