Growing window recursive quadratic optimization with variable regularization

Asad A. Ali; Jesse B. Hoagg; Magnus Mossberg; Dennis S. Bernstein

doi:10.1109/CDC.2010.5717527

Growing window recursive quadratic optimization with variable regularization

Asad A. Ali, Jesse B. Hoagg, Magnus Mossberg, Dennis S. Bernstein

Mechanical and Aerospace Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Scopus citations

Abstract

We present a growing-window variable-regularization recursive least squares (GW-VR-RLS) algorithm. Standard recursive least squares (RLS) uses a time-invariant regularization. More specifically, the inverse of the initial covariance matrix in classical RLS can be viewed as a regularization term, which weights the difference between the next state estimate and the initial state estimate. The present paper allows for time-varying in the weighting as well as what is being weighted. This extension can be used to modulate the speed of convergence of the estimates versus the magnitude of transient estimation errors. Furthermore, the regularization term can weight the difference between the next state estimate and a time-varying vector of parameters rather than the initial state estimate as is required in standard RLS.

Original language	English
Title of host publication	2010 49th IEEE Conference on Decision and Control, CDC 2010
Pages	496-501
Number of pages	6
DOIs	https://doi.org/10.1109/CDC.2010.5717527
State	Published - 2010
Event	49th IEEE Conference on Decision and Control, CDC 2010 - Atlanta, United States Duration: Dec 15 2010 → Dec 17 2010

Publication series

Name	Proceedings of the IEEE Conference on Decision and Control
ISSN (Print)	0743-1546
ISSN (Electronic)	2576-2370

Conference

Conference	49th IEEE Conference on Decision and Control, CDC 2010
Country/Territory	United States
City	Atlanta
Period	12/15/10 → 12/17/10

ASJC Scopus subject areas

Control and Systems Engineering
Modeling and Simulation
Control and Optimization

Access to Document

10.1109/CDC.2010.5717527

Cite this

@inproceedings{d252d615270242e397835aea86988fbc,

title = "Growing window recursive quadratic optimization with variable regularization",

abstract = "We present a growing-window variable-regularization recursive least squares (GW-VR-RLS) algorithm. Standard recursive least squares (RLS) uses a time-invariant regularization. More specifically, the inverse of the initial covariance matrix in classical RLS can be viewed as a regularization term, which weights the difference between the next state estimate and the initial state estimate. The present paper allows for time-varying in the weighting as well as what is being weighted. This extension can be used to modulate the speed of convergence of the estimates versus the magnitude of transient estimation errors. Furthermore, the regularization term can weight the difference between the next state estimate and a time-varying vector of parameters rather than the initial state estimate as is required in standard RLS.",

author = "Ali, \{Asad A.\} and Hoagg, \{Jesse B.\} and Magnus Mossberg and Bernstein, \{Dennis S.\}",

year = "2010",

doi = "10.1109/CDC.2010.5717527",

language = "English",

isbn = "9781424477456",

series = "Proceedings of the IEEE Conference on Decision and Control",

pages = "496--501",

booktitle = "2010 49th IEEE Conference on Decision and Control, CDC 2010",

note = "49th IEEE Conference on Decision and Control, CDC 2010 ; Conference date: 15-12-2010 Through 17-12-2010",

}

Ali, AA, Hoagg, JB, Mossberg, M & Bernstein, DS 2010, Growing window recursive quadratic optimization with variable regularization. in 2010 49th IEEE Conference on Decision and Control, CDC 2010., 5717527, Proceedings of the IEEE Conference on Decision and Control, pp. 496-501, 49th IEEE Conference on Decision and Control, CDC 2010, Atlanta, United States, 12/15/10. https://doi.org/10.1109/CDC.2010.5717527

Growing window recursive quadratic optimization with variable regularization. / Ali, Asad A.; Hoagg, Jesse B.; Mossberg, Magnus et al.
2010 49th IEEE Conference on Decision and Control, CDC 2010. 2010. p. 496-501 5717527 (Proceedings of the IEEE Conference on Decision and Control).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Growing window recursive quadratic optimization with variable regularization

AU - Ali, Asad A.

AU - Hoagg, Jesse B.

AU - Mossberg, Magnus

AU - Bernstein, Dennis S.

PY - 2010

Y1 - 2010

N2 - We present a growing-window variable-regularization recursive least squares (GW-VR-RLS) algorithm. Standard recursive least squares (RLS) uses a time-invariant regularization. More specifically, the inverse of the initial covariance matrix in classical RLS can be viewed as a regularization term, which weights the difference between the next state estimate and the initial state estimate. The present paper allows for time-varying in the weighting as well as what is being weighted. This extension can be used to modulate the speed of convergence of the estimates versus the magnitude of transient estimation errors. Furthermore, the regularization term can weight the difference between the next state estimate and a time-varying vector of parameters rather than the initial state estimate as is required in standard RLS.

AB - We present a growing-window variable-regularization recursive least squares (GW-VR-RLS) algorithm. Standard recursive least squares (RLS) uses a time-invariant regularization. More specifically, the inverse of the initial covariance matrix in classical RLS can be viewed as a regularization term, which weights the difference between the next state estimate and the initial state estimate. The present paper allows for time-varying in the weighting as well as what is being weighted. This extension can be used to modulate the speed of convergence of the estimates versus the magnitude of transient estimation errors. Furthermore, the regularization term can weight the difference between the next state estimate and a time-varying vector of parameters rather than the initial state estimate as is required in standard RLS.

UR - http://www.scopus.com/inward/record.url?scp=79953142512&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79953142512&partnerID=8YFLogxK

U2 - 10.1109/CDC.2010.5717527

DO - 10.1109/CDC.2010.5717527

M3 - Conference contribution

AN - SCOPUS:79953142512

SN - 9781424477456

T3 - Proceedings of the IEEE Conference on Decision and Control

SP - 496

EP - 501

BT - 2010 49th IEEE Conference on Decision and Control, CDC 2010

T2 - 49th IEEE Conference on Decision and Control, CDC 2010

Y2 - 15 December 2010 through 17 December 2010

ER -

Growing window recursive quadratic optimization with variable regularization

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this