人工智能培训

搜索

深度学习论文:聚类光谱算法的改进分析(Improved Analysis of Spectral Algorithm for Clustering)

[复制链接]
imissa 发表于 2019-12-9 13:10:18 | 显示全部楼层 |阅读模式
imissa 2019-12-9 13:10:18 152 0 显示全部楼层
深度学习论文:聚类光谱算法的改进分析(Improved Analysis of Spectral Algorithm for Clustering)频谱算法是图划分算法,它通过使用频谱嵌入图将图的节点集划分为组。基于该算法的聚类技术被称为光谱聚类,并广泛用于数据分析中。为了更好地理解为什么光谱聚类成功,Peng等人。 (2015年)以及Kolev和Mehlhorn(2016年)研究了一类图的某种光谱算法的行为,该图称为良好聚类图。具体来说,他们在图形上放了一个假设,并说明了频谱算法在性能上的性能保证。他们研究的算法使用了Shiand Malic(2000)开发的频谱嵌入图。在本文中,我们改进了它们的结果,在较弱的假设下提供了更好的性能保证。我们还利用Ng等人开发的光谱嵌入图评估了光谱算法的性能。 (2002)。
Spectral algorithms are graph partitioning algorithms that partition a nodeset of a graph into groups by using a spectral embedding map.Clusteringtechniques based on the algorithms are referred to as spectral clustering andare widely used in data analysis.To gain a better understanding of whyspectral clustering is successful, Peng et al.(2015) and Kolev and Mehlhorn(2016) studied the behavior of a certain type of spectral algorithm for a classof graphs, called well-clustered graphs.Specifically, they put an assumptionon graphs and showed the performance guarantee of the spectral algorithm underit.The algorithm they studied used the spectral embedding map developed by Shiand Malic (2000).In this paper, we improve on their results, giving a betterperformance guarantee under a weaker assumption.We also evaluate theperformance of the spectral algorithm with the spectral embedding map developedby Ng et al.(2002).深度学习论文:聚类光谱算法的改进分析(Improved Analysis of Spectral Algorithm for Clustering)
URL地址:https://arxiv.org/abs/1912.02997     ----pdf下载地址:https://arxiv.org/pdf/1912.02997    ----深度学习论文:聚类光谱算法的改进分析(Improved Analysis of Spectral Algorithm for Clustering)
回复

使用道具 举报

您需要登录后才可以回帖 登录 | 立即注册

本版积分规则 返回列表 发新帖

imissa当前离线
新手上路

查看:152 | 回复:0

快速回复 返回顶部 返回列表