arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.08779math.OCcs.DCeess.SP
收藏

关于常步长梯度推进算法在有向图上的收敛性结果

On the convergence result of the gradient-push algorithm on directed graphs with constant stepsize

Woocheol Choi, Doheon Kim, Seok-Bae Yun

AI总结:

针对有向图分布式优化中常步长梯度推进算法收敛性未明确的问题,本文证明步长α小于特定值时其指数收敛到优化器O(α)邻域(基于光滑强凸成本),并通过数值实验验证,且发现其收敛速度可能快于Push-DIGing算法。

摘要:

分布式优化因其在各领域的广泛应用而备受关注,它由多个通过图连接的智能体组成,以协作方式优化总成本。在实际应用中,智能体的连接图通常是有向图。梯度推进(gradient-push)算法是有向图分布式优化的基础方法。尽管该算法在文献中被广泛使用,但在步长为常数且定义域为整个空间这一重要情况下,其收敛性尚未得到充分证明。本文证明:当步长α>0且小于某个特定值时,梯度推进算法会指数级快速收敛到优化器的O(α)邻域。该结果的前提是每个成本函数光滑且总成本函数强凸。本文提供了数值实验以支持这一理论收敛结果,还展示了一项数值测试:梯度推进算法接近极小值点小邻域的速度可能快于Push-DIGing算法——后者是梯度推进算法的变体,涉及智能体梯度信息的通信。

英文摘要:

Distributed optimization has recieved a lot of interest due to its wide applications in various fields. It consists of multiple agents that connected by a graph and optimize a total cost in a collaborative way. Often in the applications, the graph of the agents is given by a directed graph. The gradient-push algorithm is a fundamental method for distributed optimization for which the agents are connected by a directed graph. Despite of its wide usage in the literatures, its convergence property has not been established well for the important case that the stepsize is constant and the domain is the entire space. This work proves that the gradient-push algorithm with stepsize $α>0$ converges exponentially fast to an $O(α)$-neighborhood of the optimizer if the stepsize $α$ is less than a specific value. For the result, we assume that each cost is smooth and the total cost is strongly convex. Numerical experiments are provided to support the theoretical convergence result. \textcolor{black}{We also present a numerical test showing that the gradient-push algorithm may approach a small neighborhood of the minimizer faster than the Push-DIGing algorithm which is a variant of the gradient-push algorithm involving the communication of the gradient informations of the agents.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑