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 2110.06992math.OC
收藏

簇网络上分散梯度法的收敛速度

Convergence Rates of Decentralized Gradient Methods over Cluster Networks

Amit Dutta, Nila Masrourisaadat, Thinh T. Doan

摘要:

我们提出了一个分散的共识为基础的梯度(DCG)方法解决最优化问题的集群网络的节点的性能分析。这种类型的网络由许多密集连接的集群组成,它们之间具有稀疏连接。集群网络上的分散算法被观察到构成了两个时间尺度的动态,其中任何集群内的信息混合速度都比跨集群的信息混合速度快得多。基于这一观察,我们提出了一种新的分析研究集群网络上的DCG方法的收敛性。特别是,我们表明,这些方法收敛速度$\ln(T)/T$和规模的集群,这是相对较小的网络的大小的数量。我们的结果改进了现有的分析,这些方法显示出随着网络的大小而扩展。在我们的分析中的关键技术是考虑一个新的李雅普诺夫函数,捕捉多个时间尺度动态的影响,这种方法的收敛性。我们还说明了我们的理论结果,通过一些数值模拟使用DCG方法在不同的集群网络。

英文摘要:

We present an analysis for the performance of decentralized consensus-based gradient (DCG) methods for solving optimization problems over a cluster network of nodes. This type of network is composed of a number of densely connected clusters with a sparse connection between them. Decentralized algorithms over cluster networks have been observed to constitute two-time-scale dynamics, where information within any cluster is mixed much faster than the one across clusters. Based on this observation, we present a novel analysis to study the convergence of the DCG methods over cluster networks. In particular, we show that these methods converge at a rate $\ln(T)/T$ and only scale with the number of clusters, which is relatively small to the size of the network. Our result improves the existing analysis, where these methods are shown to scale with the size of the network. The key technique in our analysis is to consider a novel Lyapunov function that captures the impact of multiple time-scale dynamics on the convergence of this method. We also illustrate our theoretical results by a number of numerical simulations using DCG methods over different cluster networks.

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。

↑