网络上分布式Optimization的分治算法
A Divide-and-Conquer Algorithm for Distributed Optimization on Networks
摘要:
在本文中,我们考虑网络的拓扑结构描述的一些连接无向图${\mathcal{G}}=(V, E)$和一些代理(融合中心)配备了处理能力和本地对等通信,和最优化问题$\min_{\boldsymbol x}\big\{F({\boldsymbol x})=\sum_{i\in V}f_i({\boldsymbol x})\big\}$与本地目标函数$f_i$只取决于相邻变量的顶点$i\in V$。我们引入了一个分而治之的算法来解决上述最优化问题在一个分布式和分散的方式。提出的分治算法具有指数收敛性,其计算成本几乎是线性的网络的大小,它可以完全实现在融合中心的网络。我们的数值实验也表明,所提出的分治算法具有优越的性能比流行的分散最优化方法做最小二乘问题与/无$\ell^1$罚款。
英文摘要:
In this paper, we consider networks with topologies described by some connected undirected graph ${\mathcal{G}}=(V, E)$ and with some agents (fusion centers) equipped with processing power and local peer-to-peer communication, and optimization problem $\min_{\boldsymbol x}\big\{F({\boldsymbol x})=\sum_{i\in V}f_i({\boldsymbol x})\big\}$ with local objective functions $f_i$ depending only on neighboring variables of the vertex $i\in V$. We introduce a divide-and-conquer algorithm to solve the above optimization problem in a distributed and decentralized manner. The proposed divide-and-conquer algorithm has exponential convergence, its computational cost is almost linear with respect to the size of the network, and it can be fully implemented at fusion centers of the network. Our numerical demonstrations also indicate that the proposed divide-and-conquer algorithm has superior performance than popular decentralized optimization methods do for the least squares problem with/without $\ell^1$ penalty.
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。