On weighted subspace estimates in system identification

J. F. Cardoso; P. Loubaton; E. Moulines

On weighted subspace estimates in system identification

J. F. Cardoso
, P. Loubaton
, E. Moulines

Telecom Paris

Research output: Contribution to conference › Paper › peer-review

Abstract

Subspace based estimates, i.e. estimates obtained by exploiting the orthogonality between a set of vector statistics and a set of parameter-dependent vectors have gained much popularity in the signal processing literature. The purpose of this contribution is to develop a general theory for such estimates. We in particular discuss the generalization of the optimal weighted subspace fitting approach, introduced by Viberg [2] in the DOA estimation context. We then establish that the optimally weighted estimate enjoy some invariance properties.

Original language	English
Pages	352-355
Number of pages	4
Publication status	Published - 1 Jan 1996
Event	Proceedings of the 1996 8th IEEE Signal Processing Workshop on Statistical Signal and Array Processing, SSAP'96 - Corfu, Greece Duration: 24 Jun 1996 → 26 Jun 1996

Conference

Conference	Proceedings of the 1996 8th IEEE Signal Processing Workshop on Statistical Signal and Array Processing, SSAP'96
City	Corfu, Greece
Period	24/06/96 → 26/06/96

Cite this

@conference{d619b706f1844bb886563f1facd192a8,

title = "On weighted subspace estimates in system identification",

abstract = "Subspace based estimates, i.e. estimates obtained by exploiting the orthogonality between a set of vector statistics and a set of parameter-dependent vectors have gained much popularity in the signal processing literature. The purpose of this contribution is to develop a general theory for such estimates. We in particular discuss the generalization of the optimal weighted subspace fitting approach, introduced by Viberg [2] in the DOA estimation context. We then establish that the optimally weighted estimate enjoy some invariance properties.",

author = "Cardoso, \{J. F.\} and P. Loubaton and E. Moulines",

year = "1996",

month = jan,

day = "1",

language = "English",

pages = "352--355",

note = "Proceedings of the 1996 8th IEEE Signal Processing Workshop on Statistical Signal and Array Processing, SSAP'96 ; Conference date: 24-06-1996 Through 26-06-1996",

}

TY - CONF

T1 - On weighted subspace estimates in system identification

AU - Cardoso, J. F.

AU - Loubaton, P.

AU - Moulines, E.

PY - 1996/1/1

Y1 - 1996/1/1

N2 - Subspace based estimates, i.e. estimates obtained by exploiting the orthogonality between a set of vector statistics and a set of parameter-dependent vectors have gained much popularity in the signal processing literature. The purpose of this contribution is to develop a general theory for such estimates. We in particular discuss the generalization of the optimal weighted subspace fitting approach, introduced by Viberg [2] in the DOA estimation context. We then establish that the optimally weighted estimate enjoy some invariance properties.

AB - Subspace based estimates, i.e. estimates obtained by exploiting the orthogonality between a set of vector statistics and a set of parameter-dependent vectors have gained much popularity in the signal processing literature. The purpose of this contribution is to develop a general theory for such estimates. We in particular discuss the generalization of the optimal weighted subspace fitting approach, introduced by Viberg [2] in the DOA estimation context. We then establish that the optimally weighted estimate enjoy some invariance properties.

M3 - Paper

AN - SCOPUS:0029697126

SP - 352

EP - 355

T2 - Proceedings of the 1996 8th IEEE Signal Processing Workshop on Statistical Signal and Array Processing, SSAP'96

Y2 - 24 June 1996 through 26 June 1996

ER -

On weighted subspace estimates in system identification

Abstract

Conference

Fingerprint

Cite this