arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.01460cs.SIcs.SYeess.SYmath.OC
收藏

聚类如何影响网络上分散式优化的收敛性:一种基于蒙特卡洛的方法

How Clustering Affects the Convergence of Decentralized Optimization over Networks: A Monte-Carlo-based Approach

Mohammadreza Doostmohammadian, Shahaboddin Kharazmi, Hamid R. Rabiee

AI总结:

本文通过随机无标度与聚类无标度网络建模,结合蒙特卡洛仿真和真实网络特征谱分析,发现低聚类网络具有更高的分散式优化收敛速度,并指出可通过调节网络聚类提升分散式机器学习的学习速率。

摘要:

由于云计算、物联网(IoT)、智能交通网络以及传感器网络并行处理的进步,分散式算法引起了广泛关注。这类算法的收敛性与底层网络拓扑的特定性质直接相关。具体而言,已知聚类系数会影响例如网络上的可控性/可观测性以及流行病增长。在本工作中,我们研究聚类系数对网络化优化方法收敛速度的影响。为此,我们通过随机无标度(SF)网络和聚类无标度(CSF)网络来建模大规模分布式系统的结构,并通过调节网络聚类系数来比较收敛速度。这一过程保持其他相关网络性质(如幂律度分布、链路数量和平均度)不变。基于蒙特卡洛的仿真用于在大量SF图拓扑试验中比较收敛速度。此外,为了研究真实案例中的收敛速度,我们将一些真实世界网络的聚类系数与底层网络的特征谱(作为收敛速度的度量)进行比较。结果有趣地表明,低聚类网络上具有更高的收敛速度。这一点具有重要意义,因为可以通过调节网络聚类来提高许多现有分散式机器学习场景的学习速率。

英文摘要:

Decentralized algorithms have gained substantial interest owing to advancements in cloud computing, Internet of Things (IoT), intelligent transportation networks, and parallel processing over sensor networks. The convergence of such algorithms is directly related to specific properties of the underlying network topology. Specifically, the clustering coefficient is known to affect, for example, the controllability/observability and the epidemic growth over networks. In this work, we study the effects of the clustering coefficient on the convergence rate of networked optimization approaches. In this regard, we model the structure of large-scale distributed systems by random scale-free (SF) and clustered scale-free (CSF) networks and compare the convergence rate by tuning the network clustering coefficient. This is done by keeping other relevant network properties (such as power-law degree distribution, number of links, and average degree) unchanged. Monte-Carlo-based simulations are used to compare the convergence rate over many trials of SF graph topologies. Furthermore, to study the convergence rate over real case studies, we compare the clustering coefficient of some real-world networks with the eigenspectrum of the underlying network (as a measure of convergence rate). The results interestingly show higher convergence rate over low-clustered networks. This is significant as one can improve the learning rate of many existing decentralized machine-learning scenarios by tuning the network clustering.

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。

↑