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 2602.16148math.OCcs.LG
收藏

用于分布式非光滑优化的局部适应-然后-结合算法:实现可证明的通信加速

Local adapt-then-combine algorithms for distributed nonsmooth optimization: Achieving provable communication acceleration

School of Computer Science and Engineering, Suzhou University of Technology(苏州科技大学计算机科学与工程学院);School of Mathematics, Southeast University(东南大学数学学院);School of Cyber Science and Engineering, Southeast University(东南大学网络科学与工程学院)

Luyao Guo, Xinli Shi, Wenying Xu, Jinde Cao

AI总结:

本文提出了一种通信高效的FlexATC框架,实现分布式非光滑优化中的可证明通信加速。

摘要:

本文关注网络上的分布式复合优化问题,其中代理旨在最小化局部光滑组件的和以及一个公共的非光滑项。利用概率局部更新机制,我们提出了一种通信高效的适应-然后-结合(ATC)框架,即FlexATC,统一了多种基于ATC的分布式算法。在步长独立于网络拓扑和局部更新次数的情况下,我们建立了FlexATC在凸和强凸设置下的次线性和线性收敛速度。值得注意的是,在强凸设置下,线性速率与目标函数和网络拓扑解耦,且FlexATC允许在大多数迭代中跳过通信而不影响线性速率。此外,所提出的统一理论首次证明了局部更新可证明地导致ATC类分布式算法的通信加速。数值实验进一步验证了所提框架的有效性,并证实了理论结果。

英文摘要:

This paper is concerned with the distributed composite optimization problem over networks, where agents aim to minimize a sum of local smooth components and a common nonsmooth term. Leveraging the probabilistic local updates mechanism, we propose a communication-efficient Adapt-Then-Combine (ATC) framework, FlexATC, unifying numerous ATC-based distributed algorithms. Under stepsizes independent of the network topology and the number of local updates, we establish sublinear and linear convergence rates for FlexATC in convex and strongly convex settings, respectively. Remarkably, in the strong convex setting, the linear rate is decoupled from the objective functions and network topology, and FlexATC permits communication to be skipped in most iterations without any deterioration of the linear rate. In addition, the proposed unified theory demonstrates for the first time that local updates provably lead to communication acceleration for ATC-based distributed algorithms. Numerical experiments further validate the efficacy of the proposed framework and corroborate the theoretical results.

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。

↑