arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1603.06478cs.LGcs.DS
收藏

基于高斯混合模型的硬聚类

Hard-Clustering with Gaussian Mixture Models

Paderborn University(帕德博恩大学)

Johannes Blömer, Sascha Brauer, Kathrin Bujna

摘要:

训练统计模型的参数来描述给定的数据集是数据采掘和机器学习领域的中心任务。最大似然估计(MLE)是一种非常流行和强大的参数估计方法。最广泛使用的统计模型是混合模型,特别是高斯分布的混合模型。MLE问题的一个流行的硬聚类变体是所谓的完全数据最大似然估计(CMLE)方法。解决CMLE问题的标准方法是分类期望最大化(CEM)算法。不幸的是,它只能保证算法收敛到目标函数的某个(可能是任意差的)稳定点。在本文中,我们提出了两个算法的限制版本的CMLE问题。也就是说,我们的算法近似合理的解决方案CMLE问题,满足一定的自然属性。此外,他们计算的解决方案,其成本(即完整数据对数似然值)最多是一个因素$(1+ε)$比我们搜索的解决方案的成本。注意,CMLE问题在其最一般的,即不受限制的形式中没有很好地定义,并且允许可以被认为是退化解的平凡最优解。

英文摘要:

Training the parameters of statistical models to describe a given data set is a central task in the field of data mining and machine learning. A very popular and powerful way of parameter estimation is the method of maximum likelihood estimation (MLE). Among the most widely used families of statistical models are mixture models, especially, mixtures of Gaussian distributions. A popular hard-clustering variant of the MLE problem is the so-called complete-data maximum likelihood estimation (CMLE) method. The standard approach to solve the CMLE problem is the Classification-Expectation-Maximization (CEM) algorithm. Unfortunately, it is only guaranteed that the algorithm converges to some (possibly arbitrarily poor) stationary point of the objective function. In this paper, we present two algorithms for a restricted version of the CMLE problem. That is, our algorithms approximate reasonable solutions to the CMLE problem which satisfy certain natural properties. Moreover, they compute solutions whose cost (i.e. complete-data log-likelihood values) are at most a factor $(1+ε)$ worse than the cost of the solutions that we search for. Note the CMLE problem in its most general, i.e. unrestricted, form is not well defined and allows for trivial optimal solutions that can be thought of as degenerated solutions.

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。

↑