Distributed learning via Diffusion adaptation with application to ensemble learning.

We examine the problem of learning a set of parameters from a distributed dataset. We assume the datasets are collected by agents over a distributed ad-hoc network, and that the communication of the actual raw data is prohibitive due to either privacy constraints or communication constraints. We propose a distributed algorithm for online learning that is proved to guarantee a bounded excess risk and the bound can be made arbitrary small for sufficiently small step-sizes. We apply our framework to the expert advice problem where nodes learn the weights for the trained experts distributively.


Published in:
European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, 245-250
Presented at:
European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium, April 25-27, 2012
Year:
2012
ISBN:
978-2-87419-04
Laboratories:




 Record created 2017-12-19, last modified 2018-03-17


Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)