Latency Aware Distributed ADMM over Networks

Abstract

Methods based on the alternating direction method of multipliers (ADMM) has attracted academic attention because of its excellent convergence performance and potential application scenarios in many machine learning or optimization fields. However, classical distributed ADMM algorithm assumed ideal network communication, which do not consider the impact of network delay on computing performance. In this paper, based on the strategy of selecting bridges with lowest network latency and appropriate iterative process, we propose a latency aware distributed ADMM algorithm to alleviate the impact of network delay. The classical algorithm and proposed algorithm are tested and compared in real network scenarios. Experiments show that the proposed algorithm reduces the running time and improves the computing performance. Especially in networks with large delay, the effect is more obvious.