Show simple item record

dc.contributor.authorAlrashdi, Ayed
dc.contributor.authorSifaou, Houssem
dc.contributor.authorKammoun, Abla
dc.contributor.authorAlouini, Mohamed-Slim
dc.contributor.authorAl-Naffouri, Tareq Y.
dc.date.accessioned2020-09-14T11:50:16Z
dc.date.available2020-09-14T11:50:16Z
dc.date.issued2020-08-29
dc.identifier.urihttp://hdl.handle.net/10754/665125
dc.description.abstractIn this paper, we consider the problem of recovering a sparse signal from noisy linear measurements using the so called LASSO formulation. We assume a correlated Gaussian design matrix with additive Gaussian noise. We precisely analyze the high dimensional asymptotic performance of the LASSO under correlated design matrices using the Convex Gaussian Min-max Theorem (CGMT). We define appropriate performance measures such as the mean-square error (MSE), probability of support recovery, element error rate (EER) and cosine similarity.
dc.publisherarXiv
dc.relation.urlhttps://arxiv.org/pdf/2008.13033
dc.rightsArchived with thanks to arXiv
dc.titlePrecise Error Analysis of the LASSO under Correlated Designs
dc.typePreprint
dc.contributor.departmentCommunication Theory Lab
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentElectrical Engineering
dc.contributor.departmentElectrical Engineering Program
dc.eprint.versionPre-print
dc.contributor.institutionElectrical Engineering Department, University of Hail, Hail, Saudi Arabia.
dc.identifier.arxivid2008.13033
kaust.personAlrashdi, Ayed Mofareh Bakheet
kaust.personSifaou, Houssem
kaust.personKammoun, Abla
kaust.personAlouini, Mohamed-Slim
kaust.personAl-Naffouri, Tareq Y.
refterms.dateFOA2020-09-14T11:50:40Z


Files in this item

Thumbnail
Name:
Preprintfile1.pdf
Size:
279.4Kb
Format:
PDF
Description:
Pre-print

This item appears in the following Collection(s)

Show simple item record