Consistent parameter estimation for LASSO and approximate message passing

dc.citation.firstpage119en_US
dc.citation.issueNumber1en_US
dc.citation.journalTitleThe Annals of Statisticsen_US
dc.citation.lastpage148en_US
dc.citation.volumeNumber46en_US
dc.contributor.authorMousavi, Alien_US
dc.contributor.authorMaleki, Arianen_US
dc.contributor.authorBaraniuk, Richard G.en_US
dc.date.accessioned2018-07-11T19:50:55Zen_US
dc.date.available2018-07-11T19:50:55Zen_US
dc.date.issued2018en_US
dc.description.abstractThis paper studies the optimal tuning of the regularization parameter in LASSO or the threshold parameters in approximate message passing (AMP). Considering a model in which the design matrix and noise are zero-mean i.i.d. Gaussian, we propose a data-driven approach for estimating the regularization parameter of LASSO and the threshold parameters in AMP. Our estimates are consistent, that is, they converge to their asymptotically optimal values in probability as nn, the number of observations, and pp, the ambient dimension of the sparse vector, grow to infinity, while n/pn/p converges to a fixed number δδ. As a byproduct of our analysis, we will shed light on the asymptotic properties of the solution paths of LASSO and AMP.en_US
dc.identifier.citationMousavi, Ali, Maleki, Arian and Baraniuk, Richard G.. "Consistent parameter estimation for LASSO and approximate message passing." <i>The Annals of Statistics,</i> 46, no. 1 (2018) Institute of Mathematical Statistics: 119-148. https://doi.org/10.1214/17-AOS1544.en_US
dc.identifier.doihttps://doi.org/10.1214/17-AOS1544en_US
dc.identifier.urihttps://hdl.handle.net/1911/102399en_US
dc.language.isoengen_US
dc.publisherInstitute of Mathematical Statisticsen_US
dc.rightsArticle is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.en_US
dc.titleConsistent parameter estimation for LASSO and approximate message passingen_US
dc.typeJournal articleen_US
dc.type.dcmiTexten_US
dc.type.publicationpublisher versionen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
ParameterEstimation.pdf
Size:
360.14 KB
Format:
Adobe Portable Document Format
Description: