A unifying tutorial on Approximate Message Passing
Statistics Theory
2021-05-11 v1 Information Theory
math.IT
Machine Learning
Statistics Theory
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
@article{arxiv.2105.02180,
title = {A unifying tutorial on Approximate Message Passing},
author = {Oliver Y. Feng and Ramji Venkataramanan and Cynthia Rush and Richard J. Samworth},
journal= {arXiv preprint arXiv:2105.02180},
year = {2021}
}
Comments
99 pages, 2 figures