A Modified Gradient Flow for Distributed Convex Optimization on Directed Networks
Mohammad Jahvani, Martin Guay · 2022 American Control Conference (ACC) · 2022
This paper considers the distributed convex optimization problem over directed multi-agent networks. We introduce a modified version of the distributed gradient descent method in continuous-time setting. In contrast to the existing literature, we do not assume that agents have any a–priori knowledge about their "out-degrees". We show that the proposed network flow is guaranteed to converge, on any strongly connected digraph, to the global minimizer of a sum of convex functions provided that the aggregate objective function is strongly convex, the local cost functions have Lipschitz-continuous gradients.