Projection approximation subspace tracking
- 1 January 1995
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 43 (1) , 95-107
- https://doi.org/10.1109/78.365290
Abstract
Subspace estimation plays an important role in a variety of modern signal processing applications. We present a new approach for tracking the signal subspace recursively. It is based on a novel interpretation of the signal subspace as the solution of a projection like unconstrained minimization problem. We show that recursive least squares techniques can be applied to solve this problem by making an appropriate projection approximation. The resulting algorithms have a computational complexity of O(nr) where n is the input vector dimension and r is the number of desired eigencomponents. Simulation results demonstrate that the tracking capability of these algorithms is similar to and in some cases more robust than the computationally expensive batch eigenvalue decomposition. Relations of the new algorithms to other subspace tracking methods and numerical issues are also discussedKeywords
This publication has 25 references indexed in Scilit:
- Adaptive algorithms for estimating eigenvectors of correlation type matricesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Rotation-based RLS algorithms: unified derivations, numerical properties, and parallel implementationsIEEE Transactions on Signal Processing, 1992
- Noniterative subspace trackingIEEE Transactions on Signal Processing, 1992
- Eigenvalues and eigenvectors of covariance matrices for signals closely spaced in frequencyIEEE Transactions on Signal Processing, 1992
- Updating Singular Value Decompositions. A Parallel Implementation.Published by SPIE-Intl Soc Optical Eng ,1989
- Adaptive eigensubspace algorithms for direction or frequency estimation and trackingIEEE Transactions on Acoustics, Speech, and Signal Processing, 1988
- Estimating the covariance matrix by signal subspace averagingIEEE Transactions on Acoustics, Speech, and Signal Processing, 1986
- A complex gradient operator and its application in adaptive array theoryIEE Proceedings H Microwaves, Optics and Antennas, 1983
- Simplified neuron model as a principal component analyzerJournal of Mathematical Biology, 1982
- Rank-one modification of the symmetric eigenproblemNumerische Mathematik, 1978