A unifying tutorial on Approximate Message Passing

Oliver Feng, Ramji Venkataramanan, Cynthia G. Rush, Richard J. Samworth

Research output: Book/ReportBook

36 Citations (SciVal)

Abstract

Over the last decade or so, Approximate Message Passing (AMP) algorithms have become extremely popular in various structured high-dimensional statistical problems. Although the origins of these techniques can be traced back to notions of belief propagation in the statistical physics literature, our goals in this work are to present the main ideas of AMP from a statistical perspective and 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.
Original languageEnglish
Place of PublicationU. S. A.
PublisherNow Publishers Inc
ISBN (Print)9781638280040
DOIs
Publication statusPublished - 30 May 2022

Publication series

NameFoundations and Trends® in Machine Learning
No.4
Volume15

Fingerprint

Dive into the research topics of 'A unifying tutorial on Approximate Message Passing'. Together they form a unique fingerprint.

Cite this