Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Distributed Adaptive Learning With Multiple Kernels in Diffusion Networks

 
: Shin, B.-S.; Yukawa, M.; Cavalcante, R.L.G.; Dekorsy, A.

:

IEEE transactions on signal processing 66 (2018), No.21, pp.5505-5519
ISSN: 0096-3518
ISSN: 0018-9278
ISSN: 0096-1620
ISSN: 1053-587X
English
Journal Article
Fraunhofer HHI ()

Abstract
We propose an adaptive scheme for distributed learning of nonlinear functions by a network of nodes. The proposed algorithm consists of a local adaptation stage utilizing multiple kernels with projections onto hyperslabs and a diffusion stage to achieve consensus on the estimates over the whole network. Multiple kernels are incorporated to enhance the approximation of functions with several high- and low-frequency components common in practical scenarios. We provide a thorough convergence analysis of the proposed scheme based on the metric of the Cartesian product of multiple reproducing kernel Hilbert spaces. To this end, we introduce a modified consensus matrix considering this specific metric and prove its equivalence to the ordinary consensus matrix. Besides, the use of hyperslabs enables a significant reduction of the computational demand with only a minor loss in the performance. Numerical evaluations with synthetic and real data are conducted showing the efficacy of the proposed algorithm compared to the state-of-the-art schemes.

: http://publica.fraunhofer.de/documents/N-524209.html