Title :
Convergence analysis of a mixed controlled L2−LP adaptive algorithm
Author :
Zidouri, Abdelmalek
Author_Institution :
Dept. of Electr. Eng., King Fahd Univ. of Pet. & Miner., Dhahran, Saudi Arabia
Abstract :
A new adaptive scheme for system identification is proposed. The derivation of the algorithm and its convexity property are detailed. Also, the first moment behaviour as well as the second moment behaviour of the weights are studied. Bounds for the step size on the convergence of the proposed algorithm are derived, as well as the steady-state analysis is carried out. Finally, simulation results are performed and are found to corroborate with the theory developed.
Keywords :
adaptive control; adaptive systems; convergence; convex programming; adaptive scheme; convergence analysis; convexity property; mixed controlled adaptive algorithm; moment behaviour; steady state analysis; system identification; Adaptive algorithms; Algorithm design and analysis; Convergence; Laplace equations; Least squares approximations; Noise; Signal processing algorithms; Adaptive Algorithm; Convergence; LMS Algorithm; Mixed norm; lp-norm;
Conference_Titel :
Signal Processing Conference, 2010 18th European
Conference_Location :
Aalborg
