TL;DR这篇研究论文通过使用正则化技术,解决了高维数据应用中 EM 算法在 M 步时无法定义的问题,并在此基础上,具有统计保证的处理了高维混合回归、缺失变量回归等问题。
Abstract
latent variable models are a fundamental modeling tool in machine learning
applications, but they present significant computational and analytical
challenges. The popular em algorithm and its variants, is a much