...
首页> 外文期刊>IEEE Transactions on Automatic Control >Distributed Second-Order Methods With Increasing Number of Working Nodes
【24h】

Distributed Second-Order Methods With Increasing Number of Working Nodes

机译:随着越来越多的工作节点的分布二阶方法

获取原文
获取原文并翻译 | 示例
           

摘要

Recently, an idling mechanism has been introduced in the context of distributed first order methods for minimization of a sum of nodes' local convex costs over a generic, connected network. With the idling mechanism, each node i, at each iteration k, is active-updates its solution estimate and exchanges messages with its network neighborhood-with probability p(k), and it stays idle with probability 1 - p(k), while the activations are independent both across nodes and across iterations. In this paper, we demonstrate that the idling mechanism can be successfully incorporated in distributed second-order methods also. Specifically, we apply the idling mechanism to the recently proposed distributed quasi-Newton (DQN) method. We show that, when p(k) grows to one across iterations geometrically, DQN with idling exhibits very similar theoretical convergence and convergence rates properties as the standard DQN method, thus achieving the same order of convergence rate (R-linear) as the standard DQN, but with significantly cheaper updates.
机译:最近,在分布式第一订单方法的上下文中引入了一种空闲机制,以最小化通用连接网络的节点本地凸起成本的总和。利用空闲机制,每个节点I在每个迭代k处都是主动更新其解决方案估计和与其网络邻域与概率p(k)的消息交换,并且它与概率1 - p(k)保持空闲,而激活在节点和跨迭代中都是独立的。在本文中,我们证明了怠速机制也可以成功地以分布式的二阶方法纳入其中。具体而言,我们将空转机制应用于最近提出的分布式准牛顿(DQN)方法。我们表明,当P(k)在几何上几何上生长到一个时,具有怠速的DQN具有非常相似的理论会聚和收敛速率属性作为标准DQN方法,从而实现了与标准相同的收敛速度顺序(R-Linear)。 DQN,但具有更便宜的更新。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号