arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.08709math.OCcs.DCcs.SYeess.SY
收藏

一阶分布式优化算法的规范形式

A Canonical Form for First-Order Distributed Optimization Algorithms

University of Wisconsin–Madison(威斯康星大学麦迪逊分校);Wisconsin Institute for Discovery(威斯康星发现研究所)

Akhil Sundararajan, Bryan Van Scoy, Laurent Lessard

AI总结:

本文提出了一种规范形式,用于描述任何可以在每个迭代中使用一次通信和梯度计算的分布式优化算法,每个代理最多存储两个状态变量,该形式通过一组最小的参数能够系统地分析和设计分布式优化算法。

摘要:

我们考虑了一个分布式优化问题,其中网络中的代理试图最小化局部函数的平均值。为了解决这个问题,近年来提出了几种算法,其中代理执行各种组合的与邻居通信、局部梯度计算和本地状态变量的更新。在本文中,我们提出了一种规范形式,该形式可以描述任何可以在每个迭代中使用一次通信和梯度计算的分布式算法,其中每个代理最多存储两个状态变量。该规范形式包含一组最小的参数,这些参数既独特又具有足够的表达能力,能够捕捉此类类别的任何分布式算法。我们规范形式的通用性使分布式优化算法的系统分析和设计成为可能。

英文摘要:

We consider the distributed optimization problem in which a network of agents aims to minimize the average of local functions. To solve this problem, several algorithms have recently been proposed where agents perform various combinations of communication with neighbors, local gradient computations, and updates to local state variables. In this paper, we present a canonical form that characterizes any first-order distributed algorithm that can be implemented using a single round of communication and gradient computation per iteration, and where each agent stores up to two state variables. The canonical form features a minimal set of parameters that are both unique and expressive enough to capture any distributed algorithm in this class. The generic nature of our canonical form enables the systematic analysis and design of distributed optimization algorithms.

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。

↑