Clustering is a widely used technique in machine learning, however, relatively little research in consistency of clustering algorithms has been done so far. In this paper we investigate the consistency of the regularized spectral clustering algorithm, which has been proposed recently. It provides a ...
Consistency of spectral clustering in stochastic block models We analyze the performance of spectral clustering for community extraction in stochastic block models. We show that, under mild conditions, spectral cluste... J Lei,A Rinaldo - 《Annals of Statistics》 被引量: 242发表: 2015年 ...
然后做了图的Cheeger cut的consistency Consistency of Cheeger and ratio graph cuts,preprint 分析了谱聚类的consistency A variational approach to the consistency of spectral clustering,Applied and Computational Harmonic Analysis,preprint,published 以及他们最近推广到了lp和error rate了[我还没看 Error estimates f...
SPECTRAL CLUSTERING AND THE HIGH-DIMENSIONAL STOCHASTIC BLOCKMODEL1 connected components as the clusters. Like the Girvan-Newman algorithm, spec- tral clustering is a "nonparametric" algorithm motivated by the following insights and heuristics: spectral clustering is a convex relaxation of the normalized...
摘要: We propose a simple and efficient modifica-tion of the popular DBSCAN clustering algo-rithm. This modification is able to detect the most interesting vertical threshold level in an automated, data-driven way. We establish both consistency and optimal learning rates for this modification....
Single cell RNA sequencing is a promising technique to determine the states of individual cells and classify novel cell subtypes. In current sequence data analysis, however, genes with low expressions are omitted, which leads to inaccurate gene counts an
Multi-view spectral clustering, which aims at yielding an agreement or consensus data objects grouping across multi-views with their graph laplacian matric... Y Wang,W Zhang,L Wu,... - AAAI Press 被引量: 93发表: 2016年 Low-Rank Common Subspace for Multi-view Learning Multi-view data is ...
the representation learning and spectral clustering in two separated steps, which also limits its performance. Based on these observations, we introduce a novel position-aware exclusivity term to exploit the complementary information and an indicator consistency term to unify the processing of ...
due to the effect of each sample not being the same when the response is involved. Another interesting fact is that the formula of the LC-Stat is similar to the objective function in spectral clustering [23], which aims at finding a best cut for a given graph structure. Spectral clustering...
The nuclear force is based on the Skyrme-Hartree-Fock energy functional carried consistently through all steps of modelling. The main effect of phonon coupling is a broadening of the spectral distributions (collisional width). This broadening is particularly dramatic for low-lying dipole strength in ...