Loading...
Loading...

Go to the content (press return)

Asymptotically optimal linear shrinkage of sample LMMSE and MVDR filters

Author
Serra, J.; Najar, M.
Type of activity
Journal article
Journal
IEEE transactions on signal processing
Date of publication
2014-07-15
Volume
62
Number
14
First page
3552
Last page
3564
DOI
https://doi.org/10.1109/TSP.2014.2329420 Open in new window
Project funding
GRE3N-LINK-MAC. Conceptos radio generales para comunicaciones móviles eficientes energéticamente: aspectos de las capas de enlace y de acceso al medio
Repository
http://hdl.handle.net/2117/24612 Open in new window
URL
http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6827237 Open in new window
Abstract
Conventional implementations of the linearminimum mean-square (LMMSE) and minimum variance distortionless response (MVDR) estimators rely on the sample matrix inversion (SMI) technique, i.e., on the sample covariance matrix (SCM). This approach is optimal in the large sample size regime. Nonetheless, in small sample size situations, those sample estimators suffer a large performance degradation. Thus, the aim of this paper is to propose corrections of these sample methods that counteract their p...
Citation
Serra, J.; Najar, M. Asymptotically optimal linear shrinkage of sample LMMSE and MVDR filters. "IEEE transactions on signal processing", 15 Juliol 2014, vol. 62, núm. 14, p. 3552-3564.
Keywords
Consistent estimation, Covariance matrices, Eigenvalues, Eigenvectors, Estimators, LMMSE, MVDR, Random matrix theory, Shrinkage estimation, Signal, Wave-form
Group of research
SPCOM - Signal Processing and Communications Group

Participants