A globally convergent matricial algorithm for multivariate spectral estimation

Federico Ramponi; Augusto Ferrante; Michele Pavon

doi:10.1109/TAC.2009.2028977

A globally convergent matricial algorithm for multivariate spectral estimation

Federico Ramponi, Augusto Ferrante, Michele Pavon

Mathematics

Research output: Contribution to journal › Article › peer-review

Abstract

In 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.

Original language	English (US)
Pages (from-to)	2376-2388
Number of pages	13
Journal	IEEE Transactions on Automatic Control
Volume	54
Issue number	10
DOIs	https://doi.org/10.1109/TAC.2009.2028977
State	Published - 2009

Keywords

Convex optimization
Global convergence
Hellinger distance
Matricial Newton algorithm
Multivariable spectrum approximation
Spectral estimation

ASJC Scopus subject areas

Control and Systems Engineering
Computer Science Applications
Electrical and Electronic Engineering

Access to Document

10.1109/TAC.2009.2028977

Cite this

@article{d78fe55630044acb8bf11f29facdd3a5,

title = "A globally convergent matricial algorithm for multivariate spectral estimation",

abstract = "In 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.",

keywords = "Convex optimization, Global convergence, Hellinger distance, Matricial Newton algorithm, Multivariable spectrum approximation, Spectral estimation",

author = "Federico Ramponi and Augusto Ferrante and Michele Pavon",

year = "2009",

doi = "10.1109/TAC.2009.2028977",

language = "English (US)",

volume = "54",

pages = "2376--2388",

journal = "IEEE Transactions on Automatic Control",

issn = "0018-9286",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "10",

}

TY - JOUR

T1 - A globally convergent matricial algorithm for multivariate spectral estimation

AU - Ramponi, Federico

AU - Ferrante, Augusto

AU - Pavon, Michele

PY - 2009

Y1 - 2009

N2 - In 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.

AB - In 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.

KW - Convex optimization

KW - Global convergence

KW - Hellinger distance

KW - Matricial Newton algorithm

KW - Multivariable spectrum approximation

KW - Spectral estimation

UR - http://www.scopus.com/inward/record.url?scp=70350337948&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70350337948&partnerID=8YFLogxK

U2 - 10.1109/TAC.2009.2028977

DO - 10.1109/TAC.2009.2028977

M3 - Article

AN - SCOPUS:70350337948

SN - 0018-9286

VL - 54

SP - 2376

EP - 2388

JO - IEEE Transactions on Automatic Control

JF - IEEE Transactions on Automatic Control

IS - 10

ER -

A globally convergent matricial algorithm for multivariate spectral estimation

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this