CREDO: A Communication-Efficient Distributed Estimation Algorithm

Abstract

© 2018 IEEE. This paper presents Communication efficient REcursive Distributed estimatiOn algorithm, \mathcal{CREDO} for networked multi-agent systems. \mathcal{CREDO} caters to situations in which the agents collaboratively estimate a vector parameter by assimilating their latest sensed information and estimates from their time-varying neighborhood worker nodes over a (possibly sparse) communication graph, while adhering to a frugal communication scheme. The underlying inter-agent communication protocol is randomized and adaptively, making communications increasingly (probabilistically) sparse as time progresses. \mathcal{CREDO} may be designed to achieve at each agent a \Theta(\mathcal{C}-{t}^{-2+\zeta}) decay of the mean square error (\zeta > 0, arbitrarily small) with respect to per-node communication cost \mathcal{C}-{t}, which significantly improves over the existing \Theta(\mathcal{C}-{t}^{-1}) rates. Simulations demonstrate \mathcal{CREDO} 's communication efficiency.