BriefGPT.xyz
May, 2018
分布式特征下的监督学习
Learning Under Distributed Features
HTML
PDF
Bicheng Ying, Kun Yuan, Ali H. Sayed
TL;DR
本研究探讨了在大规模数据集和大维特征空间场景下的学习问题，通过考虑网络中代理人传播的特征信息，并提出了一种新颖的动态扩散构造、管道策略和方差减少技术相结合的分布式学习算法，能够实现在原始域中的线性收敛和全局最小值解。
Abstract
This work studies the problem of learning under both large data and large
feature space
scenarios. The feature information is assumed to be spread across agents in a
network
, where each agent observes some of the
→