Statistical Analysis of Block Coordinate Descent Algorithms for Linear Continuous-Time System Identification

Rodrigo A. Gonzalez; Koen Classens; Cristian R. Rojas; James S. Welsh; Tom Oomen

doi:10.1109/LCSYS.2024.3389939

Statistical Analysis of Block Coordinate Descent Algorithms for Linear Continuous-Time System Identification

Rodrigo A. Gonzalez^*, Koen Classens, Cristian R. Rojas, James S. Welsh, Tom Oomen

^*Corresponding author for this work

Team Jan-Willem van Wingerden

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

3 Downloads (Pure)

Abstract

Block coordinate descent is an optimization technique that is used for estimating multi-input single-output (MISO) continuous-time models, as well as single-input single output (SISO) models in additive form. Despite its widespread use in various optimization contexts, the statistical properties of block coordinate descent in continuous-time system identification have not been covered in the literature. The aim of this letter is to formally analyze the bias properties of the block coordinate descent approach for the identification of MISO and additive SISO systems. We characterize the asymptotic bias at each iteration, and provide sufficient conditions for the consistency of the estimator for each identification setting. The theoretical results are supported by simulation examples.

Original language	English
Pages (from-to)	388-393
Number of pages	6
Journal	IEEE Control Systems Letters
Volume	8
DOIs	https://doi.org/10.1109/LCSYS.2024.3389939
Publication status	Published - 2024

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

additive models
block coordinate descent
Continuous-time system identification
MISO models

Access to Document

10.1109/LCSYS.2024.3389939

Statistical_Analysis_of_Block_Coordinate_Descent_Algorithms_for_Linear_Continuous-Time_System_IdentificationFinal published version, 540 KB

Cite this

@article{c0077490cddf467caf710b3415d3bdde,

title = "Statistical Analysis of Block Coordinate Descent Algorithms for Linear Continuous-Time System Identification",

abstract = "Block coordinate descent is an optimization technique that is used for estimating multi-input single-output (MISO) continuous-time models, as well as single-input single output (SISO) models in additive form. Despite its widespread use in various optimization contexts, the statistical properties of block coordinate descent in continuous-time system identification have not been covered in the literature. The aim of this letter is to formally analyze the bias properties of the block coordinate descent approach for the identification of MISO and additive SISO systems. We characterize the asymptotic bias at each iteration, and provide sufficient conditions for the consistency of the estimator for each identification setting. The theoretical results are supported by simulation examples.",

keywords = "additive models, block coordinate descent, Continuous-time system identification, MISO models",

author = "Gonzalez, {Rodrigo A.} and Koen Classens and Rojas, {Cristian R.} and Welsh, {James S.} and Tom Oomen",

note = "Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.",

year = "2024",

doi = "10.1109/LCSYS.2024.3389939",

language = "English",

volume = "8",

pages = "388--393",

journal = "IEEE Control Systems Letters",

issn = "2475-1456",

publisher = "IEEE",

}

TY - JOUR

T1 - Statistical Analysis of Block Coordinate Descent Algorithms for Linear Continuous-Time System Identification

AU - Gonzalez, Rodrigo A.

AU - Classens, Koen

AU - Rojas, Cristian R.

AU - Welsh, James S.

AU - Oomen, Tom

N1 - Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2024

Y1 - 2024

N2 - Block coordinate descent is an optimization technique that is used for estimating multi-input single-output (MISO) continuous-time models, as well as single-input single output (SISO) models in additive form. Despite its widespread use in various optimization contexts, the statistical properties of block coordinate descent in continuous-time system identification have not been covered in the literature. The aim of this letter is to formally analyze the bias properties of the block coordinate descent approach for the identification of MISO and additive SISO systems. We characterize the asymptotic bias at each iteration, and provide sufficient conditions for the consistency of the estimator for each identification setting. The theoretical results are supported by simulation examples.

AB - Block coordinate descent is an optimization technique that is used for estimating multi-input single-output (MISO) continuous-time models, as well as single-input single output (SISO) models in additive form. Despite its widespread use in various optimization contexts, the statistical properties of block coordinate descent in continuous-time system identification have not been covered in the literature. The aim of this letter is to formally analyze the bias properties of the block coordinate descent approach for the identification of MISO and additive SISO systems. We characterize the asymptotic bias at each iteration, and provide sufficient conditions for the consistency of the estimator for each identification setting. The theoretical results are supported by simulation examples.

KW - additive models

KW - block coordinate descent

KW - Continuous-time system identification

KW - MISO models

UR - http://www.scopus.com/inward/record.url?scp=85190743716&partnerID=8YFLogxK

U2 - 10.1109/LCSYS.2024.3389939

DO - 10.1109/LCSYS.2024.3389939

M3 - Article

AN - SCOPUS:85190743716

SN - 2475-1456

VL - 8

SP - 388

EP - 393

JO - IEEE Control Systems Letters

JF - IEEE Control Systems Letters

ER -

Statistical Analysis of Block Coordinate Descent Algorithms for Linear Continuous-Time System Identification

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this