TU Darmstadt / ULB / TUbiblio

Bayesian methods for sparse RLS adaptive filters

Koeppl, H. and Kubin, G. and Paoli, G. (2003):
Bayesian methods for sparse RLS adaptive filters.
Pacific Grove, CA, USA, IEEE, In: The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003, [Online-Edition: http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumbe...],
[Conference or Workshop Item]

Abstract

This work deals with an extension of the standard recursive least squares (RLS) algorithm. It allows to prune irrelevant coefficients of a linear adaptive filter with sparse impulse response and it provides a regularization method with automatic adjustment of the regularization parameter. New update equations for the inverse auto-correlation matrix estimate are derived that account for the continuing shrinkage of the matrix size. In case of densely populated impulse responses of length M, the computational complexity of the algorithm stays O(M2) as for standard RLS while for sparse impulse responses the new algorithm becomes much more efficient through the adaptive shrinkage of the dimension of the coefficient space. The algorithm has been successfully applied to the identification of sparse channel models (as in mobile radio or echo cancellation).

Item Type: Conference or Workshop Item
Erschienen: 2003
Creators: Koeppl, H. and Kubin, G. and Paoli, G.
Title: Bayesian methods for sparse RLS adaptive filters
Language: English
Abstract:

This work deals with an extension of the standard recursive least squares (RLS) algorithm. It allows to prune irrelevant coefficients of a linear adaptive filter with sparse impulse response and it provides a regularization method with automatic adjustment of the regularization parameter. New update equations for the inverse auto-correlation matrix estimate are derived that account for the continuing shrinkage of the matrix size. In case of densely populated impulse responses of length M, the computational complexity of the algorithm stays O(M2) as for standard RLS while for sparse impulse responses the new algorithm becomes much more efficient through the adaptive shrinkage of the dimension of the coefficient space. The algorithm has been successfully applied to the identification of sparse channel models (as in mobile radio or echo cancellation).

Volume: 2
Place of Publication: Pacific Grove, CA, USA
Publisher: IEEE
Divisions: 18 Department of Electrical Engineering and Information Technology > Institute for Telecommunications > Bioinspired Communication Systems
18 Department of Electrical Engineering and Information Technology
18 Department of Electrical Engineering and Information Technology > Institute for Telecommunications
Event Title: The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003
Date Deposited: 04 Apr 2014 12:35
Official URL: http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumbe...
Export:

Optionen (nur für Redakteure)

View Item View Item