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 1901.05682math.OC
收藏

分布式Optimization的精确类谱梯度法

Exact Spectral-Like Gradient Method for Distributed Optimization

Dusan Jakovetic, Natasa Krejic, Natasa Krklec Jerinkic

摘要:

自80年代末首次提出以来,谱梯度法一直受到人们的关注,特别是由于其在各种大规模应用中的优异数值性能。然而,到目前为止,它们还没有在分布式优化的上下文中得到充分的探索。在本文中,我们考虑无约束分布式最优化问题,其中$n$节点构成一个任意连接的网络,并合作最小化其局部凸费用函数的总和。在这种情况下,从现有的精确分布式梯度方法的建设,我们提出了一种新的精确分布式梯度法,其中节点的步长设计根据新的规则类似于那些在谱梯度法。我们将所提出的方法称为分布式谱梯度法(DSG)。该方法在节点局部代价和算法步长的标准假设下具有R-线性收敛。我们通过仿真示例说明了该方法的性能。

英文摘要:

Since the initial proposal in the late 80s, spectral gradient methods continue to receive significant attention, especially due to their excellent numerical performance on various large scale applications. However, to date, they have not been sufficiently explored in the context of distributed optimization. In this paper, we consider unconstrained distributed optimization problems where $n$ nodes constitute an arbitrary connected network and collaboratively minimize the sum of their local convex cost functions. In this setting, building from existing exact distributed gradient methods, we propose a novel exact distributed gradient method wherein nodes' step-sizes are designed according to the novel rules akin to those in spectral gradient methods. We refer to the proposed method as Distributed Spectral Gradient method (DSG). The method exhibits R-linear convergence under standard assumptions for the nodes' local costs and safeguarding on the algorithm step-sizes. We illustrate the method's performance through simulation examples.

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。

↑