ML Anthology

On Hyper-Parameter Estimation in Empirical Bayes: A Revisit of the MacKay Algorithm

Chune Li, Yongyi Mao, Richong Zhang, Jinpeng Huai
UAI 2016
/uai/2016/li2016uai-hyper/

Abstract

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.

PDF UAI Semantic Scholar

Cite

Text

Li et al. "On Hyper-Parameter Estimation in Empirical Bayes: A Revisit of the MacKay Algorithm." Conference on Uncertainty in Artificial Intelligence, 2016.

Markdown

[Li et al. "On Hyper-Parameter Estimation in Empirical Bayes: A Revisit of the MacKay Algorithm." Conference on Uncertainty in Artificial Intelligence, 2016.](https://mlanthology.org/uai/2016/li2016uai-hyper/)

BibTeX

@inproceedings{li2016uai-hyper,
  title     = {{On Hyper-Parameter Estimation in Empirical Bayes: A Revisit of the MacKay Algorithm}},
  author    = {Li, Chune and Mao, Yongyi and Zhang, Richong and Huai, Jinpeng},
  booktitle = {Conference on Uncertainty in Artificial Intelligence},
  year      = {2016},
  url       = {https://mlanthology.org/uai/2016/li2016uai-hyper/}
}