Towards an $O(\frac{1}{t})$ convergence rate for distributed dual averaging

Abstract: Recently, distributed dual averaging has received increasing attention due to its superiority in handling constraints and dynamic networks in multiagent optimization. However, all distributed dual averaging methods reported so far considered nonsmooth problems and have a convergence rate of $O(\frac{1}{\sqrt{t}})$. To achieve an improved convergence guarantee for smooth problems, this work proposes a second-order consensus scheme that assists each agent to locally track the global dual variable more accurately. This new scheme in conjunction with smoothness of the objective ensures that the accumulation of consensus error over time caused by incomplete global information is bounded from above. Then, a rigorous investigation of dual averaging with inexact gradient oracles is carried out to compensate the consensus error and achieve an $O(\frac{1}{t})$ convergence rate. The proposed method is examined in a large-scale LASSO problem.