The LASSO Risk for Gaussian Matrices

We consider the problem of learning a coefficient vector x ο ∈ R N from noisy linear observation y = Ax o + ∈ R n . In many contexts (ranging from model selection to image processing), it is desirable to construct a sparse estimator x̂. In this case, a popular approach consists in solving an ℓ 1 -pe...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on information theory Ročník 58; číslo 4; s. 1997 - 2017
Hlavní autoři: Bayati, M., Montanari, A.
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York, NY IEEE 01.04.2012
Institute of Electrical and Electronics Engineers
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
ISSN:0018-9448, 1557-9654
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract We consider the problem of learning a coefficient vector x ο ∈ R N from noisy linear observation y = Ax o + ∈ R n . In many contexts (ranging from model selection to image processing), it is desirable to construct a sparse estimator x̂. In this case, a popular approach consists in solving an ℓ 1 -penalized least-squares problem known as the LASSO or basis pursuit denoising. For sequences of matrices A of increasing dimensions, with independent Gaussian entries, we prove that the normalized risk of the LASSO converges to a limit, and we obtain an explicit expression for this limit. Our result is the first rigorous derivation of an explicit formula for the asymptotic mean square error of the LASSO for random instances. The proof technique is based on the analysis of AMP, a recently developed efficient algorithm, that is inspired from graphical model ideas. Simulations on real data matrices suggest that our results can be relevant in a broad array of practical applications.
AbstractList We consider the problem of learning a coefficient vector $x_{0}in{BBR}^{N}$ from noisy linear observation $y=Ax_{0}+win{BBR}^{n}$ . In many contexts (ranging from model selection to image processing), it is desirable to construct a sparse estimator ${widehat x}$. In this case, a popular approach consists in solving an $ell_{1}$ -penalized least-squares problem known as the LASSO or basis pursuit denoising. [PUBLICATION ABSTRACT]
We consider the problem of learning a coefficient vector x ο ∈ R N from noisy linear observation y = Ax o + ∈ R n . In many contexts (ranging from model selection to image processing), it is desirable to construct a sparse estimator x̂. In this case, a popular approach consists in solving an ℓ 1 -penalized least-squares problem known as the LASSO or basis pursuit denoising. For sequences of matrices A of increasing dimensions, with independent Gaussian entries, we prove that the normalized risk of the LASSO converges to a limit, and we obtain an explicit expression for this limit. Our result is the first rigorous derivation of an explicit formula for the asymptotic mean square error of the LASSO for random instances. The proof technique is based on the analysis of AMP, a recently developed efficient algorithm, that is inspired from graphical model ideas. Simulations on real data matrices suggest that our results can be relevant in a broad array of practical applications.
Author Montanari, A.
Bayati, M.
Author_xml – sequence: 1
  givenname: M.
  surname: Bayati
  fullname: Bayati, M.
  email: bayati@stanford.edu
  organization: Grad. Sch. of Bus., Stanford Univ., Stanford, CA, USA
– sequence: 2
  givenname: A.
  surname: Montanari
  fullname: Montanari, A.
  email: montanari@stanford.edu
  organization: Dept. of Electr. Eng., Stanford Univ., Stanford, CA, USA
BackLink http://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=25721928$$DView record in Pascal Francis
BookMark eNp9kEFLwzAUgIMouE3vgpcieuxMXtqkOY6hczAZuHoOr2mCmbOdSXfw39ux6cGDp8eD73sPviE5bdrGEnLF6Jgxqu7LeTkGytgYmMwEgxMyYHkuUyXy7JQMKGVFqrKsOCfDGNf9muUMBuS2fLPJYrJaLZMXH98T14ZkhrsYPTbJM3bBGxsvyJnDTbSXxzkir48P5fQpXSxn8-lkkRoOtEsrQFGLStamkkZVtmBO1VJiBbXgFCm3VHLDFBaAUkJFM0prELmpuSscl3xEbg53t6H93NnY6XW7C03_UitQvQywh-6OEEaDGxewMT7qbfAfGL405BKYgqLnxIEzoY0xWKeN77DzbdMF9BvNqN6H0304vQ-nj-F6kf4Rf27_o1wfFG-t_cUFFarIFf8GrlN3bw
CODEN IETTAW
CitedBy_id crossref_primary_10_1109_TIT_2019_2893254
crossref_primary_10_1214_20_AOS2038
crossref_primary_10_1007_s10208_021_09531_x
crossref_primary_10_1109_TIT_2024_3481956
crossref_primary_10_1214_19_AOS1923
crossref_primary_10_1109_TIT_2021_3083733
crossref_primary_10_1214_17_AOS1604
crossref_primary_10_1109_TIT_2020_2971211
crossref_primary_10_1088_1742_5468_ac9831
crossref_primary_10_1109_TIT_2020_2990880
crossref_primary_10_1186_s13634_018_0565_5
crossref_primary_10_1214_19_AOS1906
crossref_primary_10_1214_23_AOS2309
crossref_primary_10_1109_TIT_2023_3307553
crossref_primary_10_1214_24_AOS2449
crossref_primary_10_1109_TIT_2021_3138772
crossref_primary_10_1214_23_AOS2301
crossref_primary_10_1109_TIT_2022_3161227
crossref_primary_10_1214_21_AOS2100
crossref_primary_10_1214_21_AOS2101
crossref_primary_10_1214_22_AOS2246
crossref_primary_10_1214_22_AOS2243
crossref_primary_10_1109_TIT_2020_3025272
crossref_primary_10_1093_biomet_asab052
crossref_primary_10_1109_TIT_2025_3560070
crossref_primary_10_1109_TIT_2021_3095375
crossref_primary_10_1109_TSP_2013_2286775
crossref_primary_10_1073_pnas_1802705116
crossref_primary_10_1016_j_sigpro_2016_12_007
crossref_primary_10_1093_biomet_asy032
crossref_primary_10_1214_23_AOS2274
crossref_primary_10_1109_TIT_2018_2840720
crossref_primary_10_1214_25_AOS2489
crossref_primary_10_1214_14_AAP1010
crossref_primary_10_1109_TIT_2024_3450002
crossref_primary_10_1214_17_AOS1544
crossref_primary_10_1214_24_AOS2372
crossref_primary_10_1214_17_AOS1549
crossref_primary_10_1109_TIT_2013_2274513
crossref_primary_10_1109_TIT_2022_3166720
crossref_primary_10_1109_TIT_2022_3222913
crossref_primary_10_1007_s10955_019_02292_6
crossref_primary_10_1109_TIT_2022_3188753
crossref_primary_10_1109_TIT_2025_3541281
crossref_primary_10_1109_TIT_2015_2399924
crossref_primary_10_1214_13_AOS1141
crossref_primary_10_1214_23_AOS2327
crossref_primary_10_1007_s00440_015_0675_z
crossref_primary_10_1111_stan_12274
crossref_primary_10_1214_17_AOS1651
crossref_primary_10_1214_22_AOS2180
crossref_primary_10_1073_pnas_1306110110
crossref_primary_10_3150_21_BEJ1401
crossref_primary_10_1109_TIT_2013_2289865
crossref_primary_10_1007_s00440_016_0754_9
crossref_primary_10_1214_13_AOS1199
crossref_primary_10_1109_TIT_2020_2998577
crossref_primary_10_1088_2632_2153_acb428
crossref_primary_10_1109_LSP_2019_2897215
crossref_primary_10_1093_jrsssb_qkae092
crossref_primary_10_1214_24_AOS2476
crossref_primary_10_1214_25_AOS2544
crossref_primary_10_1016_j_sigpro_2016_08_009
crossref_primary_10_1088_1742_5468_ade137
crossref_primary_10_1214_15_AOS1397
crossref_primary_10_1088_1742_5468_aab051
crossref_primary_10_1007_s10208_015_9278_4
crossref_primary_10_1109_JSAC_2022_3144748
crossref_primary_10_1007_s11749_023_00870_1
crossref_primary_10_1109_TIT_2021_3049172
crossref_primary_10_1109_TIT_2013_2239356
crossref_primary_10_1088_1742_5468_ad0221
crossref_primary_10_1007_s10208_018_9395_y
crossref_primary_10_1109_TSP_2012_2225057
crossref_primary_10_1007_s00440_025_01364_x
crossref_primary_10_1214_17_AOS1630
crossref_primary_10_1137_19M1310013
crossref_primary_10_1111_rssb_12374
crossref_primary_10_1088_1742_5468_adb1d6
crossref_primary_10_1093_jrsssb_qkae117
crossref_primary_10_1109_TIT_2011_2165823
crossref_primary_10_1093_jrsssb_qkae039
crossref_primary_10_1111_sjos_12568
crossref_primary_10_1007_s00440_018_00896_9
crossref_primary_10_1137_17M1113874
crossref_primary_10_1109_TIT_2017_2773497
crossref_primary_10_1109_TIT_2017_2649460
crossref_primary_10_1109_ACCESS_2022_3148329
crossref_primary_10_1088_2632_2153_acd749
crossref_primary_10_1093_imaiai_iaae024
crossref_primary_10_1093_imaiai_iaae025
crossref_primary_10_1109_TIT_2015_2457942
crossref_primary_10_1073_pnas_2302930120
crossref_primary_10_1109_TAES_2014_130733
crossref_primary_10_1109_TSP_2022_3217917
crossref_primary_10_3390_math11173706
crossref_primary_10_1109_TIT_2024_3471746
crossref_primary_10_1109_TIT_2017_2717585
crossref_primary_10_1214_25_AAP2186
crossref_primary_10_1214_16_AOS1529
crossref_primary_10_1088_1751_8121_adce65
crossref_primary_10_1007_s10107_025_02279_0
crossref_primary_10_3390_e23020178
crossref_primary_10_1109_TIT_2018_2816681
crossref_primary_10_1109_TIT_2014_2343629
crossref_primary_10_1214_16_AOS1521
crossref_primary_10_1109_TIT_2012_2205894
crossref_primary_10_1214_24_AOS2464
crossref_primary_10_1088_1742_5468_add1ce
crossref_primary_10_1109_TIT_2024_3458953
crossref_primary_10_1080_03610926_2024_2322616
Cites_doi 10.1117/12.217610
10.1214/aos/1024691081
10.1111/j.1467-9868.2011.00771.x
10.1137/080716542
10.1214/aop/1176989118
10.1093/acprof:oso/9780198570837.001.0001
10.1109/TIT.2010.2094817
10.1007/s00220-002-0783-3
10.1109/TIT.2011.2177575
10.1007/BF01199026
10.1088/1742-5468/2009/09/L09003
10.1002/ett.4460100604
10.1070/IM1977v011n02ABEH001719
10.1002/cpa.20124
10.1016/j.aim.2004.08.004
10.1214/009053606000001523
10.4171/022-1/13
10.1109/TIT.2011.2112231
10.1073/pnas.0909892106
ContentType Journal Article
Copyright 2015 INIST-CNRS
Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Apr 2012
Copyright_xml – notice: 2015 INIST-CNRS
– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Apr 2012
DBID 97E
RIA
RIE
AAYXX
CITATION
IQODW
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
DOI 10.1109/TIT.2011.2174612
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Xplore
CrossRef
Pascal-Francis
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
DatabaseTitleList Technology Research Database

Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
Applied Sciences
EISSN 1557-9654
EndPage 2017
ExternalDocumentID 2613733871
25721928
10_1109_TIT_2011_2174612
6069859
Genre orig-research
Feature
GroupedDBID -~X
.DC
0R~
29I
3EH
4.4
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABFSI
ABQJQ
ABVLG
ACGFO
ACGFS
ACGOD
ACIWK
AENEX
AETEA
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
E.L
EBS
EJD
F5P
HZ~
H~9
IAAWW
IBMZZ
ICLAB
IDIHD
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNS
RXW
TAE
TN5
VH1
VJK
AAYXX
CITATION
IQODW
RIG
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c320t-b2a6d6b7dcb7c9be81f9d77ab2d630a03e073c19a82a772b0400d265cd3f8f373
IEDL.DBID RIE
ISICitedReferencesCount 209
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000302079800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0018-9448
IngestDate Tue Oct 28 07:44:05 EDT 2025
Mon Jul 21 09:10:49 EDT 2025
Sat Nov 29 03:53:13 EST 2025
Tue Nov 18 21:35:28 EST 2025
Tue Aug 26 17:18:11 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 4
Keywords state evolution
Range finding
statistical learning
Random matrix
message passing algorithms
Image processing
Noise reduction
Model selection
Least squares problem
Algorithm
Mean square error
Learning
Message passing
Algorithm performance
Simulation
graphical models
Signal processing
random matrix theory
Compressed sensing
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
CC BY 4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c320t-b2a6d6b7dcb7c9be81f9d77ab2d630a03e073c19a82a772b0400d265cd3f8f373
Notes SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
PQID 929073227
PQPubID 36024
PageCount 21
ParticipantIDs crossref_citationtrail_10_1109_TIT_2011_2174612
proquest_journals_929073227
ieee_primary_6069859
pascalfrancis_primary_25721928
crossref_primary_10_1109_TIT_2011_2174612
PublicationCentury 2000
PublicationDate 2012-04-01
PublicationDateYYYYMMDD 2012-04-01
PublicationDate_xml – month: 04
  year: 2012
  text: 2012-04-01
  day: 01
PublicationDecade 2010
PublicationPlace New York, NY
PublicationPlace_xml – name: New York, NY
– name: New York
PublicationTitle IEEE transactions on information theory
PublicationTitleAbbrev TIT
PublicationYear 2012
Publisher IEEE
Institute of Electrical and Electronics Engineers
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: Institute of Electrical and Electronics Engineers
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref12
guo (ref15) 2009
ref11
ref10
ref17
ref16
ref19
grant (ref14) 2010
ref18
talagrand (ref28) 2010
andrew (ref1) 2007
bai (ref4) 2005
bayati (ref2) 2010
ref24
ref23
ref25
chen (ref7) 1995; 2569
ref22
ref21
zhao (ref26) 2006; 7
ledoux (ref20) 2001
ref8
ref9
donoho (ref13) 2011
ref3
ref6
ref5
schrebina (ref27) 2003; 234
References_xml – year: 2005
  ident: ref4
  publication-title: Spectral Analysis of Large Dimensional Random Matrices
– volume: 2569
  start-page: 564
  year: 1995
  ident: ref7
  article-title: Examples of basis pursuit
  publication-title: Proc SPIE
  doi: 10.1117/12.217610
– ident: ref11
  doi: 10.1214/aos/1024691081
– ident: ref25
  doi: 10.1111/j.1467-9868.2011.00771.x
– ident: ref5
  doi: 10.1137/080716542
– start-page: 33
  year: 2007
  ident: ref1
  article-title: Scalable training of <formula formulatype="inline"> <tex Notation="TeX">$l^{1}$</tex></formula>-regularized log-linear models
  publication-title: Proc 24th Int Conf Mach Learn
– start-page: 6920
  year: 2011
  ident: ref13
  publication-title: The Noise Sensitivity Phase Transition in Compressed Sensing
– ident: ref6
  doi: 10.1214/aop/1176989118
– ident: ref22
  doi: 10.1093/acprof:oso/9780198570837.001.0001
– ident: ref3
  doi: 10.1109/TIT.2010.2094817
– volume: 234
  start-page: 383
  year: 2003
  ident: ref27
  article-title: On the rigorous solution of Gardners problem
  publication-title: Commun Math Phys
  doi: 10.1007/s00220-002-0783-3
– ident: ref23
  doi: 10.1109/TIT.2011.2177575
– year: 2010
  ident: ref14
  publication-title: CVX Matlab Software for Disciplined Convex Programming Version 1 21
– ident: ref10
  doi: 10.1007/BF01199026
– ident: ref19
  doi: 10.1088/1742-5468/2009/09/L09003
– year: 2001
  ident: ref20
  publication-title: The Concentration of Measure Phenomenon
– ident: ref24
  doi: 10.1002/ett.4460100604
– start-page: 145
  year: 2010
  ident: ref2
  article-title: The LASSO risk: Asymptotic results and real world examples
  publication-title: Advances in neural information processing systems
– ident: ref17
  doi: 10.1070/IM1977v011n02ABEH001719
– ident: ref8
  doi: 10.1002/cpa.20124
– volume: 7
  start-page: 2541
  year: 2006
  ident: ref26
  article-title: On model selection consistency of Lasso
  publication-title: J Mach Learn Res
– year: 2010
  ident: ref28
  publication-title: Mean Field Models for Spin Glasses Volume I Basic Examples
– ident: ref21
  doi: 10.1016/j.aim.2004.08.004
– year: 2009
  ident: ref15
  article-title: A single-letter characterization of optimal noisy compressed sensing
  publication-title: 47th Annu Allerton Conf Communication Control and Computing
– ident: ref9
  doi: 10.1214/009053606000001523
– ident: ref16
  doi: 10.4171/022-1/13
– ident: ref18
  doi: 10.1109/TIT.2011.2112231
– ident: ref12
  doi: 10.1073/pnas.0909892106
SSID ssj0014512
Score 2.55291
Snippet We consider the problem of learning a coefficient vector x ο ∈ R N from noisy linear observation y = Ax o + ∈ R n . In many contexts (ranging from model...
We consider the problem of learning a coefficient vector $x_{0}in{BBR}^{N}$ from noisy linear observation $y=Ax_{0}+win{BBR}^{n}$ . In many contexts (ranging...
SourceID proquest
pascalfrancis
crossref
ieee
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 1997
SubjectTerms Algorithm design and analysis
Applied sciences
Calibration
Compressed sensing
Detection, estimation, filtering, equalization, prediction
Equations
Exact sciences and technology
graphical models
Image processing
Image processing systems
Information theory
Information, signal and communications theory
Mean square error methods
message passing algorithms
Noise
Noise measurement
Normal distribution
random matrix theory
Services and terminals of telecommunications
Signal and communications theory
Signal processing
Signal, noise
Sparsity
state evolution
statistical learning
Systems, networks and services of telecommunications
Telecommunications
Telecommunications and information theory
Telemetry. Remote supervision. Telewarning. Remote control
Vectors
Title The LASSO Risk for Gaussian Matrices
URI https://ieeexplore.ieee.org/document/6069859
https://www.proquest.com/docview/929073227
Volume 58
WOSCitedRecordID wos000302079800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1557-9654
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014512
  issn: 0018-9448
  databaseCode: RIE
  dateStart: 19630101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwFD5swwd9cLop1unow14E69r0kuZRxKkwh8iUvZXcCkPZZN38_Z70hkMRfCs0veRLTvKd5OQ7AAORBjIwwa06DQN0UGToxMJHIqc50a5Aryhf0H8d08kkns3YUwMu67MwWus8-Exfmct8L18t5cYslQ2RbLM4ZE1oUkqLs1r1jkEQeoUyuIcGjD5HtSXpsuH0YVpodRr6HXlkawrKc6qYiEieIShpkc3ix8Cczzaj9v_-8wD2S1ZpXxfd4BAaetGBdpWxwS4NuAN73-QHuzDAPmKPjbCj_TzP3mzkr_Yd32TmXKX9mGv36-wIXka305t7p8ya4EifuGtHEB6pSFAlBZVM6NhLmaKUC6Ii3-Wur9Gqpcd4TDhSa2GsWJEolMpP49Sn_jG0FsuFPgFbMjcUVIeREATx9bmiQSqJchV6WYJ4FgwrIBNZSoqbzBbvSe5auCxB6BMDfVJCb8FF_cRHIafxR9mugbYuV6JqQX-rrer7OPjg8EtiC3pV4yWlQWYJskCsNiH09Pe39mAXv02KmJwzaK1XG30OO_JzPc9W_byrfQGNGc4K
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1dS8MwFL3MKagPTjfFOZ192IvgXJt-pHkUcW64DZEpeyv5Kgxlk3Xz93vTdsWhCL4VmpT0JDc5N7k5F6AlYk96JrhVx76HDor026FwkchpTrQt0CtKN_RfB3Q0CicT9lSC6-IujNY6DT7TN-YxPctXc7kyW2UdJNss9NkWbPueR5zstlZxZuD5TqYN7qAJo9exPpS0WWfcH2dqnYaABw7ZWITSrComJpInCEuc5bP4MTWn60238r-WHsJBziut22wgHEFJz6pQWedssHITrsL-NwHCGrRwlFgDI-1oPU-TNwsZrPXAV4m5WWkNU_V-nRzDS_d-fNdr53kT2tIl9rItCA9UIKiSgkomdOjETFHKBVGBa3Pb1WjX0mE8JBzJtTB2rEjgS-XGYexS9wTKs_lMn4Ilme0Lqv1ACIL4ulxRL5ZE2Qr9LEGcOnTWQEYyFxU3uS3eo9S5sFmE0EcG-iiHvg5XRY2PTFDjj7I1A21RLke1Ds2Nvire4_SDEzAJ69BYd16Um2QSIQ_E3yaEnv3-1UvY7Y2Hg2jQHz02YA_bQbIInXMoLxcrfQE78nM5TRbNdNh9AXEf0VE
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=The+LASSO+Risk+for+Gaussian+Matrices&rft.jtitle=IEEE+transactions+on+information+theory&rft.au=Bayati%2C+Mohsen&rft.au=Montanari%2C+Andrea&rft.date=2012-04-01&rft.issn=0018-9448&rft.eissn=1557-9654&rft.volume=58&rft.issue=4&rft.spage=1997&rft.epage=2017&rft_id=info:doi/10.1109%2FTIT.2011.2174612&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TIT_2011_2174612
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9448&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9448&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9448&client=summon