arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1609.00951math.OCcs.ITmath.ITstat.ML
收藏

正则非负矩阵分解乘性更新算法的统一收敛性分析

A Unified Convergence Analysis of the Multiplicative Update Algorithm for Regularized Nonnegative Matrix Factorization

Renbo Zhao, Vincent Y. F. Tan

摘要:

乘性更新(MU)算法已被广泛地用于估计各种发散和正则化下的非负矩阵分解(NMF)问题中的基矩阵和系数矩阵。然而,理论上的收敛性保证只得到了一些特殊的分歧,没有正规化。在这项工作中,我们提供了一个概念上简单的,自包含的,和统一的证明适用于NMF的MU算法的收敛性与广泛的分歧和正则化。我们的主要结果显示了迭代序列(即,由MU算法产生的基和系数矩阵对)收敛到非凸NMF最优化问题的稳定点集合。我们的证明策略有可能为分析机器学习和信号处理中的类似问题开辟新的途径。

英文摘要:

The multiplicative update (MU) algorithm has been extensively used to estimate the basis and coefficient matrices in nonnegative matrix factorization (NMF) problems under a wide range of divergences and regularizers. However, theoretical convergence guarantees have only been derived for a few special divergences without regularization. In this work, we provide a conceptually simple, self-contained, and unified proof for the convergence of the MU algorithm applied on NMF with a wide range of divergences and regularizers. Our main result shows the sequence of iterates (i.e., pairs of basis and coefficient matrices) produced by the MU algorithm converges to the set of stationary points of the non-convex NMF optimization problem. Our proof strategy has the potential to open up new avenues for analyzing similar problems in machine learning and signal processing.

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。

↑