Upper bound of Bayesian generalization error in non-negative matrix factorization
Upper bound of Bayesian generalization error in non-negative matrix factorization
复制标题
DOI：
10.1016/j.neucom.2017.04.068
复制
发表时间：
2016-12
期刊：
影响因子：
6
通讯作者：
Naoki Hayashi;Sumio Watanabe
中科院分区：
文献类型：
--
作者：
Naoki Hayashi;Sumio Watanabe
非负矩阵分解(NMF)是一种新的知识发现方法，用于文本挖掘、信号处理、生物信息学和消费者分析。然而，由于它不是一个正规的统计模型，其作为学习机的基本性质还没有被阐明，导致NMF的理论优化方法还没有建立。本文研究了NMF的实对数标准门限，给出了贝叶斯学习中泛化误差的一个上界。结果表明，采用贝叶斯学习可以使矩阵分解的泛化误差小于常规统计模型。
Non-negative matrix factorization (NMF) is a new knowledge discovery method that is used for text mining, signal processing, bioinformatics, and consumer analysis. However, its basic property as a learning machine is not yet clarified, as it is not a regular statistical model, resulting that theoretical optimization method of NMF has not yet established. In this paper, we study the real log canonical threshold of NMF and give an upper bound of the generalization error in Bayesian learning. The results show that the generalization error of the matrix factorization can be made smaller than regular statistical models if Bayesian learning is applied.