Abstract
In this paper, distributed regression estimation problem with incomplete data in a time-varying multi-agent network isinvestigated. Regression estimation is carried out based on local agentinformation with incomplete in the non-ignorable mechanism. By virtue of gradient-based design and adaptive filter,a distributed algorithm is proposed to deal with aregression estimation problem with incomplete data. With the help ofconvex analysis and stochastic approximation techniques, the exactconvergence is obtained for the proposed algorithm with incomplete dataand a jointly-connected multi-agent topology. Moreover, online regretanalysis is also given for real-time learning. Then, simulationsfor the proposed algorithm are also given to demonstrate how it cansolve the estimation problem in a distributed way, even when thenetwork configuration is time-varying.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call