Paper Info
Title
Robust Reduced-Rank Adaptive Algorithm Based on Parallel Subgradient Projection and Krylov Subspace
Abstract
In this paper, we propose a novel reduced-rank adaptive filtering algorithm exploiting the Krylov subspace associated with estimates of certain statistics of input and output signals. We point out that, when the estimated statistics are erroneous (e.g., due to sudden changes of environments), the existing Krylov-subspace-based reduced-rank methods compute the point that minimizes a ldquowrongrdquo mean-square error (MSE) in the subspace. The proposed algorithm exploits the set-theoretic adaptive filtering framework for tracking efficiently the optimal point in the sense of minimizing the ldquotruerdquo MSE in the subspace. Therefore, compared with the existing methods, the proposed algorithm is more suited to adaptive filtering applications. A convergence analysis of the algorithm is performed by extending the adaptive projected subgradient method (APSM). Numerical examples demonstrate that the proposed algorithm enjoys better tracking performance than the existing methods for system identification problems.
Year
DOI
Venue
2009
10.1109/TSP.2009.2027397
IEEE Transactions on Signal Processing
Keywords
Field
DocType
adaptive filters,convergence of numerical methods,gradient methods,mean square error methods,statistical analysis,Krylov subspace method,convergence analysis,mean-square error method,parallel subgradient projection method,robust reduced-rank adaptive filtering algorithm,statistics estimation,Krylov subspace,reduced-rank adaptive filtering,set theory,subgradient methods
Krylov subspace,Mathematical optimization,Algorithm design,Subspace topology,Subgradient method,Robustness (computer science),Adaptive filter,Adaptive algorithm,System identification,Mathematics
Journal
Volume
Issue
ISSN
57
12
1053-587X
Citations 
PageRank 
References 
9
0.53
31
Authors
3
Name
Order
Citations
PageRank
Masahiro Yukawa127230.44
de Lamare, R.C.265233.42
isao yamada395374.52