TY - GEN
T1 - Decentralized Multitask Recursive Least Squares with Local Linear Constraints
AU - Cao, Xuanyu
AU - Basar, Tamer
N1 - Funding Information:
Research reported in this paper was sponsored by the Army Research Laboratory and was accomplished under Cooperative Agreement Number W911NF-17-2-0196.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/11/1
Y1 - 2020/11/1
N2 - In this paper, we study decentralized multitask recursive least squares, where each node in a network has an unknown weight vector to estimate. The weight vectors of neigh-boring nodes are related through local linear equality constraints, e.g., the flow conservation constraints in network flow control. We propose a modified dual gradient ascent algorithm, which is both decentralized and online. The mean square convergence of the algorithm is established under standard assumptions. It is shown that both the mean square deviation and the excess mean square error converge to zero at geometric rates.
AB - In this paper, we study decentralized multitask recursive least squares, where each node in a network has an unknown weight vector to estimate. The weight vectors of neigh-boring nodes are related through local linear equality constraints, e.g., the flow conservation constraints in network flow control. We propose a modified dual gradient ascent algorithm, which is both decentralized and online. The mean square convergence of the algorithm is established under standard assumptions. It is shown that both the mean square deviation and the excess mean square error converge to zero at geometric rates.
UR - http://www.scopus.com/inward/record.url?scp=85107794885&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85107794885&partnerID=8YFLogxK
U2 - 10.1109/IEEECONF51394.2020.9443392
DO - 10.1109/IEEECONF51394.2020.9443392
M3 - Conference contribution
AN - SCOPUS:85107794885
T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers
SP - 1410
EP - 1414
BT - Conference Record of the 54th Asilomar Conference on Signals, Systems and Computers, ACSSC 2020
A2 - Matthews, Michael B.
PB - IEEE Computer Society
T2 - 54th Asilomar Conference on Signals, Systems and Computers, ACSSC 2020
Y2 - 1 November 2020 through 5 November 2020
ER -