Title :
Attaining optimal batch performance via distributed processing over networks
Author :
Xiaochuan Zhao ; Sayed, Ali H.
Author_Institution :
Dept. of Electr. Eng., Univ. of California, Los Angeles, Los Angeles, CA, USA
Abstract :
This work shows how the combination weights of diffusion strategies for adaptation and learning over networks can be chosen in order for the network mean-square-error performance to match that of an optimized centralized (or batch) solution. The results show that this is possible regardless of the network topology, however sparse it is, as long as the network is connected without disjoint sub-graphs.
Keywords :
distributed processing; mean square error methods; network theory (graphs); centralized processing; distributed processing; network mean-square-error performance; network topology; optimal batch performance; Convergence; Least squares approximations; Network topology; Noise; Standards; Topology; Vectors; Diffusion adaptation; Hastings rule; MRC rule; batch processing; centralized processing;
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on
Conference_Location :
Vancouver, BC
DOI :
10.1109/ICASSP.2013.6638657
