An approach to distributed parametric learning with streaming data
An approach to distributed parametric learning with streaming data
复制标题
一种利用流数据进行分布式参数学习的方法
DOI：
--
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
T. Başar
中科院分区：
文献类型：
--
作者：
Ji Liu;Yang Liu;A. Nedić;T. Başar
本文提出了一种解决多智能体网络中一类分布式参数学习问题的方法。每个agent获取自己的私有流数据，建立局部学习模型。目标是让每个智能体通过只与邻居通信，收敛到一个共同的全局学习模型，该模型被定义为所有局部学习模型的平均值。邻居关系由一个时间相关的无向图来描述，其顶点对应于代理，其边描述邻居关系。结果表明，对于任意重复联合连接图序列，该方法使所有智能体渐近收敛到共同的全局学习模型，最坏情况下的收敛速度由局部学习的速度决定。给出了一个分布式线性回归问题和一个分布式信念平均问题作为示例。
This paper presents an approach to solve a class of distributed parametric learning problems in a multi-agent network. Each agent acquires its private streaming data to establish a local learning model. The goal is for each agent to converge to a common global learning model, defined as the average of all local ones, by communicating only with its neighbors. Neighbor relationships are described by a time-dependent undirected graph whose vertices correspond to agents and whose edges depict neighbor relationships. It is shown that for any sequence of repeatedly jointly connected graphs, the approach leads all agents to asymptotically converge to the common global learning model, and the worst-case convergence rate is determined by the speed of local learning. A distributed linear regression problem and a distributed belief averaging problem are presented as illustrative examples.