Nesterov Acceleration Gradient Algorithm For Adaptive Generalized Principal Component Extraction

An adaptive Nesterov acceleration gradient (NAG) algorithm is first developed to extract single generalized principal component (GPC) corresponding to the largest eigenvalue of a stationary sample autocorrelation matrix pencil. A deflation technique enables the proposed algorithm to extract the higher-order GPCs. The proposed algorithm enjoys the advantages of a lower computational load and a highly modular structure for efficient implementation. Simulation results are given to demonstrate the effectiveness of the proposed algorithm for extracting multiple generalized principal components.