Foundations of a Multi-way Spectral Clustering Framework for Hybrid Linear Modeling
Guangliang Chen, Gilad Lerman
备注:
40 pages. Minor changes to the previous version (mainly revised Sections 2.2 & 2.3, and added references). Accepted to the Journal of Foundations of Computational Mathematics
The problem of Hybrid Linear Modeling (HLM) is to model and segment data using a mixture of affine subspaces. Different strategies have been proposed to solve this problem, however, rigorous analysis justifying their performance is missing. This paper suggests the Theoretical Spectral Curvature Clustering (TSCC) algorithm for solving the HLM problem, and provides careful analysis to justify it. The TSCC algorithm is practically a combination of Govindu's multi-way spectral clustering framework (CVPR 2005) and Ng et al.'s spectral clustering algorithm (NIPS 2001). The main result of this paper states that if the given data is sampled from a mixture of distributions concentrated around affine subspaces, then with high sampling probability the TSCC algorithm segments well the different underlying clusters. The goodness of clustering depends on the within-cluster errors, the between-clusters interaction, and a tuning parameter applied by TSCC. The proof also provides new insights for the analysis of Ng et al. (NIPS 2001).
Hybrid clustering-classification neural network in the medical diagnostics of reactive arthritis
Kharkiv National University of Radio Electronics(哈尔科夫国立无线电电子大学);Kharkiv Medical Academia of Post-Graduate Education(哈尔科夫医学研究生教育学院);Uzhhorod National University(乌日霍罗德国立大学)
On Data-Independent Properties for Density-Based Dissimilarity Measures in Hybrid Clustering
Norwegian Centre for Integrated Care and Telemedicine, University Hospital of North Norway(挪威北部大学医院综合护理与远程医疗中心);Department of Mathematics and Statistics, IIT Kanpur(印度理工学院坎普尔分校数学与统计系);Department of Mathematics and Statistics, UiT The Arctic University of Norway(挪威北极大学数学与统计系)
A Hybrid Tsallis-Polarization Impurity Measure for Decision Trees: Theoretical Foundations and Empirical Evaluation
Emergency Department, Lille University Hospital(里尔大学医院急诊科);Lille University(里尔大学);LIRMM Montpellier University(蒙彼利埃大学LIRMM);UMontpellier(蒙彼利埃大学);CRISTAL UMR CNRS 9189 Lille University(里尔大学CRISTAL UMR CNRS 9189)
A PAC-Bayesian Analysis of Graph Clustering and Pairwise Clustering
Max Planck Institute for Biological Cybernetics(马克斯·普朗克生物控制论研究所)
我们制定加权图聚类作为一个预测问题:给定一个子集的边缘权重,我们分析的能力图聚类预测剩余的边缘权重。该公式使实际和理论上的比较不同的方法图聚类,以及比较图聚类与其他可能的方式来建模的图。我们采用了PAC-Bayesian协聚类分析(Seldin and Tishby,2008; Seldin,2009)来推导图聚类的PAC-Bayesian泛化界。该界限表明,图聚类应该优化经验数据拟合和聚类在图节点上保留的互信息之间的权衡。从信息理论考虑导出的类似权衡已经显示在实践中产生最先进的结果(Slonim等人,2005年; Yom-Tov和Slonim,2009年)。本文通过提供更好的理论基础,提出形式化的推广保证,并提供更准确的方法来处理有限样本问题,从而支持了经验证据。我们推导出一个界最小化算法,并表明它在现实生活中的问题提供了很好的结果,所得出的PAC贝叶斯界是合理的紧。