Decentralized Online Optimization with Global Objectives and Local Communication

We consider a decentralized online convex optimization problem in a network of agents, where each agent controls only a coordinate (or a part) of the global decision vector. For such a problem, we propose two decentralized variants (ODA-LM and OPDA-TV) of Nesterov's primal-dual algorithm with dual averaging. In ODA-LM, to mitigate the disagreements on the primal-vector updates, the agents implement a generalization of the local information-exchange dynamics recently proposed by Li and Marden over a static undirected graph. In OPDA-TV, the agents implement the broadcast-based push-sum dynamics over a time-varying sequence of uniformly connected digraphs. We show that the regret bounds in both cases have sublinear growth of $O(\sqrt{T})$, with the time horizon $T$, when the stepsize is of the form $1/\sqrt{t}$ and the objective functions are Lipschitz-continuous convex functions with Lipschitz gradients. We also implement the proposed algorithms on a sensor network to complement our theoretical analysis.