跳到主要导航 跳到搜索 跳到主要内容

On hyper-parameter estimation in empirical Bayes: A revisit of the MacKay algorithm

  • Chune Li
  • , Yongyi Mao
  • , Richong Zhang
  • , Jinpeng Huai*
  • *此作品的通讯作者
  • Beihang University
  • University of Ottawa

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

An iterative procedure introduced in MacKay's evidence framework is often used for estimating the hyper-parameter in empirical Bayes. Despite its effectiveness, the procedure has stayed primarily as a heuristic to date. This paper formally investigates the mathematical nature of this procedure and justifies it as a well-principled algorithm framework. This framework, which we call the MacKay algorithm, is shown to be closely related to the EM algorithm under certain Gaussian assumption.

源语言英语
主期刊名Uncertainty in Artificial Intelligence - Proceedings of the 32nd Conference, UAI 2016
编辑Alexander Ihler, Dominik Janzing
出版商Association For Uncertainty in Artificial Intelligence (AUAI)
477-486
页数10
ISBN(电子版)9780996643115
出版状态已出版 - 2016
活动32nd Conference on Uncertainty in Artificial Intelligence, UAI 2016 - Jersey City, 美国
期限: 25 6月 201629 6月 2016

出版系列

姓名32nd Conference on Uncertainty in Artificial Intelligence 2016, UAI 2016

会议

会议32nd Conference on Uncertainty in Artificial Intelligence, UAI 2016
国家/地区美国
Jersey City
时期25/06/1629/06/16

学术指纹

探究 'On hyper-parameter estimation in empirical Bayes: A revisit of the MacKay algorithm' 的科研主题。它们共同构成独一无二的学术指纹。

引用此