Finite Sample Analysis of Approximate Message Passing Algorithms
Accepted version
Peer-reviewed
Repository URI
Repository DOI
Change log
Authors
Abstract
Approximate message passing (AMP) refers to a class of efficient algorithms
for statistical estimation in high-dimensional problems such as compressed
sensing and low-rank matrix estimation. This paper analyzes the performance of
AMP in the regime where the problem dimension is large but finite. For
concreteness, we consider the setting of high-dimensional regression, where the
goal is to estimate a high-dimensional vector
Description
Keywords
Journal Title
Conference Name
Journal ISSN
1557-9654
Volume Title
Publisher
Publisher DOI
Sponsorship
Engineering and Physical Sciences Research Council (EP/N013999/1)
Isaac Newton Trust (1540 (R))