A Unifying Tutorial on Approximate Message Passing
Abstract
Over the last decade or so, Approximate Message Passing (AMP) algorithms have become extremely popular in various structured high-dimensional statistical problems. The fact that the origins of these techniques can be traced back to notions of belief propagation in the statistical physics literature lends a certain mystique to the area for many statisticians. Our goal in this work is to present the main ideas of AMP from a statistical perspective, to illustrate the power and flexibility of the AMP framework. Along the way, we strengthen and unify many of the results in the existing literature.
Cite
Text
Feng et al. "A Unifying Tutorial on Approximate Message Passing." Foundations and Trends in Machine Learning, 2022. doi:10.1561/2200000092Markdown
[Feng et al. "A Unifying Tutorial on Approximate Message Passing." Foundations and Trends in Machine Learning, 2022.](https://mlanthology.org/ftml/2022/feng2022ftml-unifying/) doi:10.1561/2200000092BibTeX
@article{feng2022ftml-unifying,
title = {{A Unifying Tutorial on Approximate Message Passing}},
author = {Feng, Oliver Y. and Venkataramanan, Ramji and Rush, Cynthia and Samworth, Richard J.},
journal = {Foundations and Trends in Machine Learning},
year = {2022},
pages = {335-536},
doi = {10.1561/2200000092},
volume = {15},
url = {https://mlanthology.org/ftml/2022/feng2022ftml-unifying/}
}