Distributed primal strategies outperform primal-dual strategies over adaptive networks

This work studies distributed primal-dual strategies for adaptation and learning over networks from streaming data. Two first-order methods are considered based on the Arrow-Hurwicz (AH) and augmented Lagrangian (AL) techniques. Several results are revealed in relation to the performance and stability of these strategies when employed over adaptive networks. It is found that these methods have worse steady-state mean-square-error performance than primal methods of the consensus and diffusion type. It is also found that the AH technique can become unstable under a partial observation model, while the other techniques are able to recover the unknown under this scenario. It is further shown that AL techniques are stable over a narrower range of step-sizes than primal strategies.


Published in:
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 3497-3501
Presented at:
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), South Brisbane, Queensland, Australia, April 19-24, 2015
Year:
2015
Publisher:
IEEE
Laboratories:




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


Rate this document:

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