Distributed primal strategies outperform primal-dual strategies over adaptive networks
作者： Zaid J. Towfic , Ali H. Sayed
DOI: 10.1109/ICASSP.2015.7178621
关键词:
摘要: 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) augmented Lagrangian (AL) techniques. Several results revealed in relation to performance stability of these when employed adaptive networks. It is found that have worse steady-state mean-square-error than primal consensus diffusion type. also AH technique can become unstable under a partial observation model, while other techniques able recover unknown this scenario. further shown AL stable narrower range step-sizes strategies.
sci-hub.se 参考文章(25)
Boris T Poljak, Introduction to optimization Optimization Software, Publications Division. ,(1987)
Sergio Barbarossa, Stefania Sardellitti, Paolo Di Lorenzo, Distributed Detection and Estimation in Wireless Sensor Networks arXiv: Distributed, Parallel, and Cluster Computing. ,vol. 2, pp. 329- 408 ,(2014) , 10.1016/B978-0-12-396500-4.00007-7
Xiaochuan Zhao, Ali H. Sayed, Performance Limits for Distributed Estimation Over LMS Adaptive Networks IEEE Transactions on Signal Processing. ,vol. 60, pp. 5107- 5124 ,(2012) , 10.1109/TSP.2012.2204985
Sheng-Yuan Tu, Ali H. Sayed, Diffusion Strategies Outperform Consensus Strategies for Distributed Estimation Over Adaptive Networks IEEE Transactions on Signal Processing. ,vol. 60, pp. 6217- 6234 ,(2012) , 10.1109/TSP.2012.2217338
Jianshu Chen, Ali H. Sayed, Diffusion Adaptation Strategies for Distributed Optimization and Learning Over Networks IEEE Transactions on Signal Processing. ,vol. 60, pp. 4289- 4305 ,(2012) , 10.1109/TSP.2012.2198470
Ali H. Sayed, Sheng-Yuan Tu, Jianshu Chen, Xiaochuan Zhao, Zaid J. Towfic, Diffusion strategies for adaptation and learning over networks: an examination of distributed strategies and network behavior IEEE Signal Processing Magazine. ,vol. 30, pp. 155- 171 ,(2013) , 10.1109/MSP.2012.2231991
Angelia Nedic, Asuman Ozdaglar, Distributed Subgradient Methods for Multi-Agent Optimization IEEE Transactions on Automatic Control. ,vol. 54, pp. 48- 61 ,(2009) , 10.1109/TAC.2008.2009515
Alec Koppel, Felicia Y. Jakubiec, Alejandro Ribeiro, A saddle point algorithm for networked online convex optimization international conference on acoustics, speech, and signal processing. pp. 8292- 8296 ,(2014) , 10.1109/ICASSP.2014.6855218
Dahir H. Dini, Danilo P. Mandic, Cooperative adaptive estimation of distributed noncircular complex signals 2012 Conference Record of the Forty Sixth Asilomar Conference on Signals, Systems and Computers (ASILOMAR). pp. 1518- 1522 ,(2012) , 10.1109/ACSSC.2012.6489281
S. Sundhar Ram, A. Nedić, V. V. Veeravalli, Distributed Stochastic Subgradient Projection Algorithms for Convex Optimization Journal of Optimization Theory and Applications. ,vol. 147, pp. 516- 545 ,(2010) , 10.1007/S10957-010-9737-7