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 1808.08366stat.MLcs.LG
收藏

高维数据的参数联合聚类

Parameter-wise co-clustering for high-dimensional data

McMaster University(麦克马斯特大学);University Lille 1(里尔第一大学)

M. P. B. Gallaugher, C. Biernacki, P. D. McNicholas

摘要:

近年来,数据维数越来越受到关注,导致许多参数和降维技术被提出在文献中。针对连续随机变量建模的数据,提出了一种基于参数的协同聚类模型。建议的模型,虽然允许更大的灵活性,仍然保持了非常高的程度的简约实现传统的共同聚类。随机期望最大化(SEM)算法以及吉布斯采样器用于参数估计和集成的完整的对数似然准则用于模型选择。模拟和真实的数据集用于说明和比较与传统的联合聚类。

英文摘要:

In recent years, data dimensionality has increasingly become a concern, leading to many parameter and dimension reduction techniques being proposed in the literature. A parameter-wise co-clustering model, for data modelled via continuous random variables, is presented. The proposed model, although allowing more flexibility, still maintains the very high degree of parsimony achieved by traditional co-clustering. A stochastic expectation-maximization (SEM) algorithm along with a Gibbs sampler is used for parameter estimation and an integrated complete log-likelihood criterion is used for model selection. Simulated and real datasets are used for illustration and comparison with traditional co-clustering.

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。

↑