Joint Model-Order and Step-Size Adaptation using Convex Combinations of Adaptive Reduced-Rank Filters

Abstract: In this work we propose schemes for joint model-order and step-size adaptation of reduced-rank adaptive filters. The proposed schemes employ reduced-rank adaptive filters in parallel operating with different orders and step sizes, which are exploited by convex combination strategies. The reduced-rank adaptive filters used in the proposed schemes are based on a joint and iterative decimation and interpolation (JIDF) method recently proposed. The unique feature of the JIDF method is that it can substantially reduce the number of coefficients for adaptation, thereby making feasible the use of multiple reduced-rank filters in parallel. We investigate the performance of the proposed schemes in an interference suppression application for CDMA systems. Simulation results show that the proposed schemes can significantly improve the performance of the existing reduced-rank adaptive filters based on the JIDF method.