ADMM-Tracking Gradient for Distributed Optimization over Asynchronous and Unreliable Networks

In this paper, we propose (i) a novel distributed algorithm for consensus optimization over networks and (ii) a robust extension tailored to deal with asynchronous agents and packet losses. The key idea is to achieve dynamic consensus on (i) the agents' average and (ii) the global descent direction by iteratively solving an online auxiliary optimization problem through a distributed implementation of the Alternating Direction Method of Multipliers (ADMM). Such a mechanism is suitably interlaced with a local proportional action steering each agent estimate to the solution of the original consensus optimization problem. First, in the case of ideal networks, by using tools from system theory, we prove the linear convergence of the scheme with strongly convex costs. Then, by exploiting the averaging theory, we extend such a first result to prove that the robust extension of our method preserves linear convergence in the case of asynchronous agents and packet losses. Further, by using the notion of Input-to-State Stability, we also guarantee the robustness of the schemes with respect to additional, generic errors affecting the agents' updates. Finally, some numerical simulations confirm our theoretical findings and show that the proposed methods outperform the existing state-of-the-art distributed methods for consensus optimization