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 1911.09714math.STstat.TH
收藏

随机邻域图上局部谱聚类的统计保证

Statistical Guarantees for Local Spectral Clustering on Random Neighborhood Graphs

Alden Green, Sivaraman Balakrishnan, Ryan J. Tibshirani

摘要:

我们研究了个性化PageRank(PPR)算法,一个本地的谱方法聚类,提取集群使用局部偏置随机游动在一个给定的种子节点。与以前的工作相比,我们采用了经典的统计学习设置,从未知的非参数分布中获取样本,并旨在识别足够突出的聚类。我们引入了三个群体水平的泛函-归一化切割,电导和局部扩散,类似于基于图形的泛函的相同的名称-并证明PPR,运行在一个邻域图,恢复集群与小人口归一化切割和大电导和局部扩散。我们应用我们的一般理论,建立PPR识别连接区域的高密度(密度集群),满足一组自然的几何条件。我们还展示了相反的结果,即PPR可能无法恢复几何条件较差的密度集群,即使是渐进的。最后,我们为我们的理论提供了实证支持。

英文摘要:

We study the Personalized PageRank (PPR) algorithm, a local spectral method for clustering, which extracts clusters using locally-biased random walks around a given seed node. In contrast to previous work, we adopt a classical statistical learning setup, where we obtain samples from an unknown nonparametric distribution, and aim to identify sufficiently salient clusters. We introduce a trio of population-level functionals -- the normalized cut, conductance, and local spread, analogous to graph-based functionals of the same name -- and prove that PPR, run on a neighborhood graph, recovers clusters with small population normalized cut and large conductance and local spread. We apply our general theory to establish that PPR identifies connected regions of high density (density clusters) that satisfy a set of natural geometric conditions. We also show a converse result, that PPR can fail to recover geometrically poorly-conditioned density clusters, even asymptotically. Finally, we provide empirical support for our theory.

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。

↑