arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.02589math.OCcs.AI
收藏

MUSIC:采用非精确与精确方法的分布式优化加速收敛

MUSIC: Accelerated Convergence for Distributed Optimization With Inexact and Exact Methods

School of Computer Science and Technology, Hubei University of Science and Technology(湖北科技学院计算机科学与技术学院);School of Electronic and Electrical Engineering, Wuhan Textile University(武汉纺织大学电子与电气工程学院);The University of Manchester(曼彻斯特大学)

Mou Wu, Haibin Liao, Zhengtao Ding, Yonggang Xiao

AI总结:

针对单梯度更新难以加速分布式优化的问题,提出MUSIC框架,融合非精确与精确方法实现多局部更新、一次组合及加速线性收敛。

摘要:

梯度型分布式优化方法已发展为在网络化智能体系统上求解最小化学习任务的最重要工具之一。然而,每次迭代仅进行一次梯度更新,难以实现实质性的收敛加速。本文提出一个名为 MUSIC 的加速框架,允许每个智能体在每次迭代中执行多次局部更新和一次组合。更重要的是,我们将非精确和精确的分布式优化方法纳入该框架,从而开发出两种新算法,它们表现出加速的线性收敛和高通信效率。严格的收敛分析揭示了非精确策略产生稳态误差的来源,并提供了有效解决方案。基于合成数据集和真实数据集的数值结果验证了我们的理论动机与分析,以及性能优势。

英文摘要:

Gradient-type distributed optimization methods have blossomed into one of the most important tools for solving a minimization learning task over a networked agent system. However, only one gradient update per iteration is difficult to achieve a substantive acceleration of convergence. In this paper, we propose an accelerated framework named as MUSIC allowing each agent to perform multiple local updates and a single combination in each iteration. More importantly, we equip inexact and exact distributed optimization methods into this framework, thereby developing two new algorithms that exhibit accelerated linear convergence and high communication efficiency. Our rigorous convergence analysis reveals the sources of steady-state errors arising from inexact policies and offers effective solutions. Numerical results based on synthetic and real datasets demonstrate both our theoretical motivations and analysis, as well as performance advantages.

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。

↑