Title | ||
---|---|---|
ANALYSIS OF EXPLICIT REGULARIZATION IN AFFINE PROJECTION ALGORITHMS: ROBUSTNESS AND OPTIMAL CHOICE |
Abstract | ||
---|---|---|
The affine projection algorithms (APA) are a family of adap- tive filters with decorrelating properties. In this paper we pro- pose the use of a time-varying explicit regularization factor instead of the classic step size control. We show that APA re- sults stable and has robust performance against disturbances and model uncertainties. This fact is shown by the H∞ op- timality and error energy bounds we provide. Finally, we find the optimal regularization choice for maximum speed of convergence. We consider first the case under independence assumptions and then with gaussian hypothesis. |
Year | Venue | Field |
---|---|---|
2004 | EUSIPCO | Convergence (routing),Algorithm,Robustness (computer science),Regularization (mathematics),Gaussian,Affine projection,Adaptive filter,Mathematics,Regularization perspectives on support vector machines |
DocType | Citations | PageRank |
Conference | 5 | 0.71 |
References | Authors | |
4 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
G. Rey | 1 | 5 | 0.71 |
Leonardo Rey Vega | 2 | 107 | 17.14 |
S. Tressens | 3 | 269 | 18.38 |
Gaetan Rey | 4 | 11 | 1.87 |