arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2007.08837math.OC
收藏

一类精确一阶分布式方法在权重平衡时变网络与非协调步长下的线性收敛速率分析

Linear Convergence Rate Analysis of a Class of Exact First-Order Distributed Methods for Weight-Balanced Time-Varying Networks and Uncoordinated Step Sizes

Greta Malaspina, Dusan Jakovetic, Natasa Krejic

AI总结:

本文分析一类精确分布式一阶方法在时变权重平衡网络与非协调步长下的R-线性收敛性,证明统一Extra、统一DIGing及精确谱梯度方法对此类设置具有高度鲁棒性。

摘要:

我们在关于底层网络和步长的一般设置下分析了一类精确分布式一阶方法。更详细地说,我们同时允许时变的非协调步长和时变的、有向的、权重平衡的网络,这些网络在有界区间上联合连通。所分析的这类方法涵盖了若干现有算法,例如统一的Extra和统一的DIGing(Jakovetic, 2019),或精确谱梯度方法(Jakovetic, Krejic, Krklec Jerinkic, 2019),这些算法此前在更严格的假设下已被分析。在所假设的设置下,我们建立了这些方法的R-线性收敛性,并提出了我们的结果对文献的若干影响。最值得注意的是,我们表明(Jakovetic, 2019)中的统一策略和(Jakovetic, Krejic, Krklec Jerinkic, 2019)中的谱步长选择策略对非协调的时变步长和时变网络表现出高度的鲁棒性。

英文摘要:

We analyze a class of exact distributed first order methods under a general setting on the underlying network and step-sizes. In more detail, we allow simultaneously for time-varying uncoordinated stepsizes and time-varying directed weight-balanced networks, jointly connected over bounded intervals. The analyzed class of methods subsumes several existing algorithms like the unified Extra and unified DIGing (Jakovetic, 2019), or the exact spectral gradient method (Jakovetic, Krejic, Krklec Jerinkic, 2019) that have been analyzed before under more restrictive assumptions. Under the assumed setting, we establish R-linear convergence of the methods and present several implications that our results have on the literature. Most notably, we show that the unification strategy in (Jakovetic, 2019) and the spectral step-size selection strategy in (Jakovetic, Krejic, Krklec Jerinkic, 2019) exhibit a high degree of robustness to uncoordinated time-varying step sizes and to time-varying networks.

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。

↑