Strong consistency of spectral clustering for stochastic block models

• المؤلفون الرئيسيون: SU, Liangjun, WANG, Wuyi, ZHANG, Yichong
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2019
• الموضوعات: Community detection; degree-corrected stochastic block model; K-means; regularization; strong consistency.; Econometrics
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/soe_research/2278; https://ink.library.smu.edu.sg/context/soe_research/article/3277/viewcontent/Strong_consistency_Stochastic_Block_modles_2019_wp.pdf
• المؤسسة: Singapore Management University

In this paper we prove the strong consistency of several methods based on the spectral clustering techniques that are widely used to study the community detection problem in stochastic block models (SBMs). We show that under some weak conditions on the minimal degree, the number of communities, and...