arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2009.12732math.OC
收藏

分布式复合材料Optimization乘子的统一近似方法

A Unifying Approximate Method of Multipliers for Distributed Composite Optimization

Xuyang Wu, Jie Lu

摘要:

本文研究了无向网络上的凸复合优化问题,其中每个节点被赋予一个光滑分量函数和一个非光滑分量函数,要求使整个网络的所有分量函数之和最小.为了解决这个问题,一个通用的近似方法的乘数(AMM)的发展,它试图近似的乘数方法凭借代理函数具有众多的选项。然后,我们设计可能的不可分离的,随时间变化的代理函数以各种方式,导致不同的分布式实现AMM。我们证明,AMM概括了十多个国家的最先进的分布式优化算法,和某些特定的设计,其代理函数的结果在各种新的算法的文献。此外,我们表明,AMM是能够实现的$O(1/k)$收敛速率的最优性,和收敛速度成为线性时,局部限制强凸和光滑的问题。这样的收敛速度为许多现有方法提供了新的或更强的收敛结果,这些方法可以被视为AMM的专门化。

英文摘要:

This paper investigates solving convex composite optimization on an undirected network, where each node, privately endowed with a smooth component function and a nonsmooth one, is required to minimize the sum of all the component functions throughout the network. To address such a problem, a general Approximate Method of Multipliers (AMM) is developed, which attempts to approximate the Method of Multipliers by virtue of a surrogate function with numerous options. We then design the possibly nonseparable, time-varying surrogate function in various ways, leading to different distributed realizations of AMM. We demonstrate that AMM generalizes more than ten state-of-the-art distributed optimization algorithms, and certain specific designs of its surrogate function result in a variety of new algorithms to the literature. Furthermore, we show that AMM is able to achieve an $O(1/k)$ rate of convergence to optimality, and the convergence rate becomes linear when the problem is locally restricted strongly convex and smooth. Such convergence rates provide new or stronger convergence results to many prior methods that can be viewed as specializations of AMM.

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。

↑