arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2111.02802stat.MLcs.LG
收藏

通信受限网络中的分布式稀疏特征选择

Distributed Sparse Feature Selection in Communication-Restricted Networks

Sharif University of Technology(谢里夫理工大学);Institute for Research in Fundamental Sciences (IPM)(基础科学研究研究所(IPM))

Hanie Barghi, Amir Najafi, Seyed Abolfazl Motahari

摘要:

本文旨在提出并理论分析一种新的分布式稀疏线性回归和特征选择方案。其主要目标是从一个未知的稀疏线性模型中学习高维数据集的几个因果特征。然而,包括$\mathbb{R}^p$中的$n$数据样本的假定训练集已经分布在具有通过极低带宽链路连接的$N$客户端的大型网络上。此外,我们考虑了$1\ll N\ll n\ll p$的渐近构型。为了从整个数据集中推断因果维度,我们提出了一种简单而有效的网络信息共享方法。在这方面,我们从理论上表明,真正的因果关系的功能可以可靠地恢复,可以忽略不计的带宽使用的$O\left(N\log p\right)$在整个网络。与将所有样本发送到单个节点的普通情况(集中式场景)相比,这产生了显著更低的通信成本,该情况需要$O\left(np\right)$传输。甚至更复杂的方案,如ADMM,仍然具有$O\left(Np\right)$的通信复杂度。令人惊讶的是,我们的样本复杂性界被证明是相同的(直到一个常数因子),在每个节点的固定性能指标的最佳集中式方法,而一个天真的分散技术与$N$线性增长。本文的理论保证基于Javanmard等人(2019)最近的去偏LASSO分析框架,并得到了在合成和真实世界数据集上进行的几个计算机实验的支持。

英文摘要:

This paper aims to propose and theoretically analyze a new distributed scheme for sparse linear regression and feature selection. The primary goal is to learn the few causal features of a high-dimensional dataset based on noisy observations from an unknown sparse linear model. However, the presumed training set which includes $n$ data samples in $\mathbb{R}^p$ is already distributed over a large network with $N$ clients connected through extremely low-bandwidth links. Also, we consider the asymptotic configuration of $1\ll N\ll n\ll p$. In order to infer the causal dimensions from the whole dataset, we propose a simple, yet effective method for information sharing in the network. In this regard, we theoretically show that the true causal features can be reliably recovered with negligible bandwidth usage of $O\left(N\log p\right)$ across the network. This yields a significantly lower communication cost in comparison with the trivial case of transmitting all the samples to a single node (centralized scenario), which requires $O\left(np\right)$ transmissions. Even more sophisticated schemes such as ADMM still have a communication complexity of $O\left(Np\right)$. Surprisingly, our sample complexity bound is proved to be the same (up to a constant factor) as the optimal centralized approach for a fixed performance measure in each node, while that of a naïve decentralized technique grows linearly with $N$. Theoretical guarantees in this paper are based on the recent analytic framework of debiased LASSO in Javanmard et al. (2019), and are supported by several computer experiments performed on both synthetic and real-world datasets.

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。

↑