A Unifying Tutorial on Approximate Message Passing
View / Open Files
Publication Date
2022Journal Title
Foundations and Trends® in Machine Learning
ISSN
1935-8237
Publisher
Now Publishers
Volume
abs/2105.02180
Type
Article
This Version
AM
Metadata
Show full item recordCitation
Feng, O. Y., Venkataramanan, R., Rush, C., & Samworth, R. J. (2022). A Unifying Tutorial on Approximate Message Passing. Foundations and Trends® in Machine Learning, abs/2105.02180 https://doi.org/10.1561/2200000092
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.
Keywords
math.ST, math.ST, cs.IT, math.IT, stat.ML, stat.TH
Sponsorship
Engineering and Physical Sciences Research Council (EP/N031938/1)
Engineering and Physical Sciences Research Council (EP/P031447/1)
Alan Turing Institute (Unknown)
Identifiers
External DOI: https://doi.org/10.1561/2200000092
This record's URL: https://www.repository.cam.ac.uk/handle/1810/335480
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.