Azam Khalili and Vahid Vahidpour and Amir Rastegarnia and Ali Farzamnia and Teo, Kenneth Tze Kin and Saeid Sanei (2021) CoordinateDescent Adaptation over Hamiltonian MultiAgent Networks. Sensors, 21. pp. 119. ISSN 19962022
Text
CoordinateDescent Adaptation over Hamiltonian MultiAgent Networks.pdf Download (38kB) 

Text
CoordinateDescent Adaptation over Hamiltonian MultiAgent Networks1.pdf Restricted to Registered users only Download (742kB)  Request a copy 
Abstract
The incremental leastmeansquare (ILMS) algorithm is a useful method to perform distributed adaptation and learning in Hamiltonian networks. To implement the ILMS algorithm, each node needs to receive the local estimate of the previous node on the cycle path to update its own local estimate. However, in some practical situations, perfect data exchange may not be possible among the nodes. In this paper, we develop a new version of ILMS algorithm, wherein in its adaptation step, only a random subset of the coordinates of update vector is available. We draw a comparison between the proposed coordinatedescent incremental LMS (CDILMS) algorithm and the ILMS algorithm in terms of convergence rate and computational complexity. Employing the energy conservation relation approach, we derive closedform expressions to describe the learning curves in terms of excess meansquareerror (EMSE) and meansquare deviation (MSD). We show that, the CDILMS algorithm has the same steadystate error performance compared with the ILMS algorithm. However, the CDILMS algorithm has a faster convergence rate. Numerical examples are given to verify the efficiency of the CDILMS algorithm and the accuracy of theoretical analysis.
Item Type:  Article 

Keyword:  Adaptive estimation , Coordinatedescent , Distributed networks , Incremental algorithm 
Subjects:  T Technology > TA Engineering (General). Civil engineering (General) > TA12040 Engineering (General). Civil engineering (General) 
Department:  FACULTY > Faculty of Engineering 
Depositing User:  SITI AZIZAH BINTI IDRIS  
Date Deposited:  22 Jun 2022 11:24 
Last Modified:  22 Jun 2022 11:24 
URI:  https://eprints.ums.edu.my/id/eprint/32939 
Actions (login required)
View Item 