Approximated power iterations for fast subspace tracking

被引：13

作者：

Badeau, R ^{[1
]}

Richard, G ^{[1
]}

David, B ^{[1
]}

Abed-Meraim, K ^{[1
]}

机构：

[1] Ecole Natl Super Telecommun Bretagne, F-75634 Paris 13, France

来源：

SEVENTH INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND ITS APPLICATIONS, VOL 2, PROCEEDINGS | 2003年

关键词：

D O I：

10.1109/ISSPA.2003.1224944

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper introduces a fast implementation of the power iterations method for subspace tracking, based on an approximation less restrictive than the well known projection approximation. This algorithm guarantees the orthonormality of the estimated subspace weighting matrix at each iteration, and satisfies a global and exponential convergence property. Moreover, it outperforms many subspace trackers related to the power method, such as PAST, NIC, NP3 and OPAST, while keeping the same computational complexity.

引用

页码：583 / 586

页数：4

共 11 条

[1] Fast orthonormal PAST algorithm [J].

Abed-Meraim, K ;

Chkeif, A ;

Hua, Y .

IEEE SIGNAL PROCESSING LETTERS, 2000, 7 (03) :60-62

[2]

BADEAU R, IN PRESS 19 C GRETSI

[3]

BADEAU R, 2003, P IEEE INT C AC SPEE

[4] Numerically-robust adaptive subspace tracking using householder transformations [J].

Douglas, SC .

SAM 2000: PROCEEDINGS OF THE 2000 IEEE SENSOR ARRAY AND MULTICHANNEL SIGNAL PROCESSING WORKSHOP, 2000, :499-503

[5]

Golub G.H., 2013, MATRIX COMPUTATIONS

[6]

Horn R. A., 1986, Matrix analysis

[7]

HUA Y, 1999, DIGITAL SIGNAL P OCT

[8] Fast subspace tracking and neural network learning by a novel information criterion [J].

Miao, YF ;

Hua, YB .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1998, 46 (07) :1967-1979

[9] Fast recursive subspace adaptive ESPRIT algorithms [J].

Strobach, P .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1998, 46 (09) :2413-2430

[10] Low-rank adaptive filters [J].

Strobach, P .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1996, 44 (12) :2932-2947

← 1 2 →