arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2203.02597math.STstat.MLstat.TH
收藏

混合模型中的错误隶属率控制

False membership rate control in mixture models

Ariane Marandon, Tabea Rebafka, Etienne Roquain, Nataliya Sokolovska

AI总结:

本文在无监督混合模型框架下提出一种控制错误隶属率(FMR)不超过预设水平$α$的插入程序,并通过理论分析和Bootstrap改进验证其有效性。

摘要:

聚类任务是将样本中的元素划分为同质组。大多数数据集包含模糊且本质上难以归入某一簇的个体。然而在实际应用中,误分类个体具有潜在灾难性,应予以避免。为保持较小的误分类率,可选择仅对部分样本进行分类。在监督学习中,该方法被称为带弃权(不执行)选项的分类。本文在无监督混合模型框架下重新审视该方法,旨在开发一种保证错误隶属率(FMR)不超过预定义名义水平$α$的方法。提出了一种插入(plug-in)程序,并提供了理论分析,通过显式余项量化FMR相对于目标水平$α$的偏差。数值实验表明,该程序的Bootstrap版本能提升性能。

英文摘要:

The clustering task consists in partitioning elements of a sample into homogeneous groups. Most datasets contain individuals that are ambiguous and intrinsically difficult to attribute to one or another cluster. However, in practical applications, misclassifying individuals is potentially disastrous and should be avoided. To keep the misclassification rate small, one can decide to classify only a part of the sample. In the supervised setting, this approach is well known and referred to as classification with an abstention option. In this paper the approach is revisited in an unsupervised mixture model framework and the purpose is to develop a method that comes with the guarantee that the false membership rate (FMR) does not exceed a pre-defined nominal level $α$. A plug-in procedure is proposed, for which a theoretical analysis is provided, by quantifying the FMR deviation with respect to the target level $α$ with explicit remainder terms. Bootstrap versions of the procedure are shown to improve the performance in numerical experiments.

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。

↑