Distributed Second-order Multi-Agent Optimization over unbalanced network without boundedness of gradients

Abstract: This paper is mainly devoted to the distributed second-order multi-agent optimization problem with unbalanced and directed networks. To deal with this problem, a new distributed algorithm is proposed based on the local neighbor information and the private objective functions. By a coordination transformation, the closed-loop system is divided into two first-order subsystems, which is easier to be dealt with. Under the assumption of the strong connectivity of networks, it is proved that all agent can collaboratively converge to some optimal solution of the team objective function, where the gradient of the private objective functions is not assumed to be bounded.