On distributed online classification in the midst of concept drifts

In this work, we analyze the generalization ability of distributed online learning algorithms under stationary and non-stationary environments. We derive bounds for the excess-risk attained by each node in a connected network of learners and study the performance advantage that diffusion has over individual non-cooperative processing. We conduct extensive simulations to illustrate the results.


Published in:
Neurocomputing, 112, 138-152
Year:
2013
Publisher:
Elsevier
ISSN:
0925-2312
Laboratories:




 Record created 2017-12-19, last modified 2018-09-13


Rate this document:

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