Generalized Distributed Dual Coordinate Ascent in a Tree Network for Machine Learning
Generalized Distributed Dual Coordinate Ascent in a Tree Network for Machine Learning
复制标题
DOI：
10.1109/icassp.2019.8682185
复制
发表时间：
2019-05
期刊：
影响因子：
--
通讯作者：
Myung Cho;L. Lai;Weiyu Xu
中科院分区：
文献类型：
--
作者：
Myung Cho;L. Lai;Weiyu Xu
随着数据量的爆炸式增长和单个位置的有限存储空间，数据通常分布在不同的位置。因此，我们面临着通过通信网络从这些分布式数据中进行大规模机器学习的挑战。本文将星星网络中的分布式对偶坐标上升推广到一般的树型网络，并给出了一般分布式对偶坐标上升的收敛速度分析。在数值实验中，我们证明了当网络的中心节点和它的直接子节点之间存在大量的通信延迟时，树型网络中的分布式对偶坐标上升的性能可以优于星星型网络中的分布式对偶坐标上升。
With explosion of data size and limited storage space at a single location, data are often distributed at different locations. We thus face the challenge of performing large-scale machine learning from these distributed data through communication networks. In this paper, we generalize the distributed dual coordinate ascent in a star network to a general tree structured network, and provide the convergence rate analysis of the general distributed dual coordinate ascent. In numerical experiments, we demonstrate that the performance of the distributed dual coordinate ascent in a tree network can outperform that of the distributed dual coordinate ascent in a star network when a network has a lot of communication delays between the center node and its direct child nodes.