Transient Analysis of Clustered Multitask Diffusion RLS Algorithm

Abstract

In this paper, we propose a novel clustered multitask diffusion RLS (MT-DRLS) algorithm over network to further improve the performance of its counterpart, the multitask diffusion LMS (MT-DLMS) algorithm. Its transient behavior is investigated, in the mean and mean-square error sense. Simulation results illustrate the significant improvement of the MT-DRLS over the MT-DLMS in terms of convergence rate and steady-state error, as well as the accuracy of the theoretical findings.

Diffusion recursive least squares algorithm based on triangular decomposition

“…While, the combined diffusion affine algorithm has been presented over the distributed networks [18], Merched [19], [20] has derived with the diffusion adaptation to fuse data based on least squares mechanism against the colored inputs in the single-task and multi-task scenes. Gao et al [21] transient behavior of a multi-task diffusion on RLS has been investigated over distributed network. Futhermore, the convergence of diffusion RLS (DRLS) has been examined against the cyclostationary colored inputs in [22].…”