A Distributed Optimization Accelerated Algorithm with Uncoordinated Time-Varying Step-Sizes in an Undirected Network

In recent years, significant progress has been made in the field of distributed optimization algorithms. This study focused on convex problem over an undirected network. The target was to minimize average all local objective functions known by each agent while communicates necessary information only with its neighbors. Based state-of-the-art algorithm, we proposed a novel when function satisfies smoothness and strong convexity. Faster convergence can be attained utilizing Nesterov Heavy-ball accelerated methods simultaneously, making algorithm widely applicable many large-scale tasks. Meanwhile, step-sizes momentum coefficients are designed as uncoordinate, time-varying, nonidentical, which make adapt wide range application scenarios. Under some assumptions conditions, through rigorous theoretical analysis, linear rate achieved. Finally, numerical experiments real dataset demonstrate superiority efficacy compared similar