dc.contributor.author Rush, Cynthia en dc.contributor.author Venkataramanan, Ramji en dc.date.accessioned 2018-05-29T12:11:11Z dc.date.available 2018-05-29T12:11:11Z dc.date.issued 2016 en dc.identifier.uri https://www.repository.cam.ac.uk/handle/1810/276254 dc.description.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 $\beta_0$ from a noisy measurement $y=A \beta_0 + w$. AMP is a low-complexity, scalable algorithm for this problem. Under suitable assumptions on the measurement matrix $A$, AMP has the attractive feature that its performance can be accurately characterized in the large system limit by a simple scalar iteration called state evolution. Previous proofs of the validity of state evolution have all been asymptotic convergence results. In this paper, we derive a concentration inequality for AMP with i.i.d.\ Gaussian measurement matrices with finite size $n \times N$. The result shows that the probability of deviation from the state evolution prediction falls exponentially in $n$. This provides theoretical support for empirical findings that have demonstrated excellent agreement of AMP performance with state evolution predictions for moderately large dimensions. The concentration inequality also indicates that the number of AMP iterations $t$ can grow no faster than order $\frac{\log n}{\log \log n}$ for the performance to be close to the state evolution predictions with high probability. The analysis can be extended to obtain similar non-asymptotic results for AMP in other settings such as low-rank matrix estimation. dc.description.sponsorship Marie Curie Career Integration Grant under Grant Agreement Number 631489. dc.publisher IEEE dc.title Finite-sample analysis of Approximate Message Passing. en dc.type Article prism.endingPage 759 prism.publicationDate 2016 en prism.publicationName ISIT en prism.startingPage 755 dc.identifier.doi 10.17863/CAM.23535 dcterms.dateAccepted 2018-03-06 en rioxxterms.version AM * rioxxterms.licenseref.uri http://www.rioxx.net/licenses/all-rights-reserved en rioxxterms.licenseref.startdate 2016 en dc.contributor.orcid Venkataramanan, Ramji [0000-0001-7915-5432] rioxxterms.type Journal Article/Review en pubs.funder-project-id European Commission (631489) dc.identifier.url http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=7532279 en rioxxterms.freetoread.startdate 2017-08-17
﻿