Online Distributed Convex Optimization on Dynamic Networks
Saghar Hosseini, Airlie Chapman, Mehran Mesbahi
IEEE TRANSACTIONS ON AUTOMATIC CONTROL | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | Published : 2016
This note presents a distributed optimization scheme over a network of agents in the presence of cost uncertainties and over switching communication topologies. Inspired by recent advances in distributed convex optimization, we propose a distributed algorithm based on dual sub-gradient averaging. A convergence rate analysis for the offline optimization, and a regret analysis for the online case, as a function of the underlying dynamic network topology are then presented for both classes of uncertainties. Application of the proposed setup is then discussed for uncertain sensor networks.
Awarded by ONR
Awarded by AFOSR
This work was supported by the ONR under Grant N00014-12-1-1002 and AFOSR Grant FA9550-12-1-0203-DEF. This work was previously presented at the IEEE Conference on Decision and Control, Firenze, Italy, December 2013. Recommended by Associate Editor Z. Chen.