Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Conferences, Workshops, Symposiums, and Seminars
  4. Distributed primal strategies outperform primal-dual strategies over adaptive networks
 
conference paper

Distributed primal strategies outperform primal-dual strategies over adaptive networks

Towfic, Zaid J.
•
Sayed, Ali H.  
2015
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

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.

  • Details
  • Metrics
Type
conference paper
DOI
10.1109/ICASSP.2015.7178621
Author(s)
Towfic, Zaid J.
Sayed, Ali H.  
Date Issued

2015

Publisher

IEEE

Published in
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Start page

3497

End page

3501

Editorial or Peer reviewed

REVIEWED

Written at

OTHER

EPFL units
ASL  
Event nameEvent placeEvent date
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

South Brisbane, Queensland, Australia

April 19-24, 2015

Available on Infoscience
December 19, 2017
Use this identifier to reference this record
https://infoscience.epfl.ch/handle/20.500.14299/143404
Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés