Distributed Online Optimization via Gradient Tracking with Adaptive Momentum

This paper deals with a network of computing agents aiming to solve an online optimization problem in a distributed fashion, i.e., by means of local computation and communication, without any central coordinator. We propose the gradient tracking with adaptive momentum estimation (GTAdam) distributed algorithm, which combines a gradient tracking mechanism with first and second order momentum estimates of the gradient. The algorithm is analyzed in the online setting for strongly convex and smooth cost functions. We prove that the average dynamic regret is bounded and that the convergence rate is linear. The algorithm is tested on a time-varying classification problem, on a (moving) target localization problem and in a stochastic optimization setup from image classification. In these numerical experiments from multi-agent learning, GTAdam outperforms state-of-the-art distributed optimization methods.