A randomized exponential canonical correlation analysis method for data analysis and dimensionality reduction

Canonical correlation analysis (CCA) is a famous data analysis method that has been successfully used in many areas. CCA extracts meaningful information from a pair of data sets, by seeking pairs of linear combinations from two sets of variables with maximum correlation. Mathematically, CCA resorts...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Applied numerical mathematics Ročník 164; s. 101 - 124
Hlavní autoři: Wu, Gang, Li, Fei
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 01.06.2021
Témata:
ISSN:0168-9274, 1873-5460
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Canonical correlation analysis (CCA) is a famous data analysis method that has been successfully used in many areas. CCA extracts meaningful information from a pair of data sets, by seeking pairs of linear combinations from two sets of variables with maximum correlation. Mathematically, CCA resorts to solving a large-scale generalized eigenvalue problem. However, as the dimension of the data sets is much larger than the number of samples, CCA may suffer from the small-sample-size (SSS) problem and the over-fitting problem. In order to overcome these difficulties, the regularized technique is often applied, but it is difficult to choose the optimal parameter in advance. In this work, we propose an Exponential Canonical Correlation Analysis (ECCA) method based on matrix exponential, which is parameter-free and can overcome the over-fitting and the SSS problems fundamentally. However, the computational overhead of the ECCA method is very high in practice. Based on the randomized singular value decomposition (RSVD), we then propose a Randomized Exponential Canonical Correlation Analysis (RECCA) method for data analysis and dimensionality reduction. Theoretical results are given to show the rationality of this randomized method, and establish the relationship between RECCA and ECCA. Numerical experiments are performed on some real-world, high-dimensional and large-sample data sets, which illustrate the superiority of the proposed algorithms over many state-of-the-art CCA algorithms.
AbstractList Canonical correlation analysis (CCA) is a famous data analysis method that has been successfully used in many areas. CCA extracts meaningful information from a pair of data sets, by seeking pairs of linear combinations from two sets of variables with maximum correlation. Mathematically, CCA resorts to solving a large-scale generalized eigenvalue problem. However, as the dimension of the data sets is much larger than the number of samples, CCA may suffer from the small-sample-size (SSS) problem and the over-fitting problem. In order to overcome these difficulties, the regularized technique is often applied, but it is difficult to choose the optimal parameter in advance. In this work, we propose an Exponential Canonical Correlation Analysis (ECCA) method based on matrix exponential, which is parameter-free and can overcome the over-fitting and the SSS problems fundamentally. However, the computational overhead of the ECCA method is very high in practice. Based on the randomized singular value decomposition (RSVD), we then propose a Randomized Exponential Canonical Correlation Analysis (RECCA) method for data analysis and dimensionality reduction. Theoretical results are given to show the rationality of this randomized method, and establish the relationship between RECCA and ECCA. Numerical experiments are performed on some real-world, high-dimensional and large-sample data sets, which illustrate the superiority of the proposed algorithms over many state-of-the-art CCA algorithms.
Author Wu, Gang
Li, Fei
Author_xml – sequence: 1
  givenname: Gang
  surname: Wu
  fullname: Wu, Gang
  email: gangwu@cumt.edu.cn, gangwu76@126.com
– sequence: 2
  givenname: Fei
  surname: Li
  fullname: Li, Fei
  email: lifei_1216@163.com
BookMark eNqFkM1qwzAQhEVJoUnaJ-hFL2B3ZdlxfOghhP5BoJfcxVpaUwVbDpJSmj597aRQ6KE97cLON8vMjE1c74ixWwGpALG426W4d4cuzSCDFKoUhLxgU7EsZVLkC5iw6aBaJlVW5ldsFsIOAIoihynrVtyjM31nP8lw-tgPxi5abLnG4YnV49Z7Ty1G2zuODttjsIF3FN96w5vec4MRfw6DGze2IxcGPbY2Hrknc9Ajfs0uG2wD3XzPOds-PmzXz8nm9ellvdokWoKMiQSz0JQ1YoHlsqlEYzRKpLqWVZkZkZckcqoQmhyLQoisBtmUtDSlLk1dGzln8myrfR-Cp0btve3QH5UANRamdupUmBoLU1CpobCBqn5R2sZT6ujRtv-w92eWhlTvlrwK2pLTZKwnHZXp7Z_8F_rjjqY
CitedBy_id crossref_primary_10_1007_s11042_023_14656_y
crossref_primary_10_1109_ACCESS_2023_3325348
crossref_primary_10_1145_3511888
crossref_primary_10_1155_2021_5589285
crossref_primary_10_1016_j_apnum_2021_04_002
crossref_primary_10_1007_s40314_025_03197_9
Cites_doi 10.1016/j.imavis.2016.06.008
10.1109/78.476433
10.1016/0304-4076(76)90010-5
10.1089/cmb.2014.0296
10.1109/TPAMI.2013.104
10.1073/pnas.0709640104
10.1016/0024-3795(79)90094-6
10.1016/0377-0427(89)90360-9
10.1137/130938700
10.1109/TSMCB.2009.2024759
10.1162/0899766042321814
10.1090/S0025-5718-1973-0348991-3
10.1186/1471-2105-11-191
10.1109/TIT.1967.1053964
10.1007/s11063-009-9123-3
10.1137/090771806
10.1007/s11222-009-9153-8
10.1109/TBME.2019.2902876
10.1137/130919222
10.3724/SP.J.1001.2008.02822
10.1006/nimg.1997.0294
10.1137/18M1183480
10.1111/j.2517-6161.1993.tb01936.x
10.1080/10556788.2019.1700257
10.1016/j.neunet.2017.11.013
10.1016/j.acha.2010.02.003
10.1080/00220973.1975.10806349
10.1137/0714065
10.1093/biomet/28.3-4.321
10.1109/TPAMI.2006.244
10.1021/ac00194a020
10.1109/TPAMI.2010.160
10.1016/j.patcog.2016.08.020
10.1016/j.csda.2013.09.020
10.1109/TIP.2013.2297020
10.1007/s12038-015-9555-z
10.1145/3136624
10.1007/BF01418329
10.1002/bimj.4710270303
ContentType Journal Article
Copyright 2020 IMACS
Copyright_xml – notice: 2020 IMACS
DBID AAYXX
CITATION
DOI 10.1016/j.apnum.2020.09.013
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISSN 1873-5460
EndPage 124
ExternalDocumentID 10_1016_j_apnum_2020_09_013
S0168927420302890
GrantInformation_xml – fundername: Fundamental Research Funds for the Central Universities of China
  grantid: 2019XKQYMS89
  funderid: https://doi.org/10.13039/501100012226
GroupedDBID --K
--M
-~X
.DC
.~1
0R~
1B1
1RT
1~.
1~5
23M
4.4
457
4G.
5GY
5VS
7-5
71M
8P~
9JN
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXUO
ABAOU
ABEFU
ABJNI
ABMAC
ABXDB
ABYKQ
ACAZW
ACDAQ
ACGFS
ACRLP
ADBBV
ADEZE
ADGUI
ADIYS
ADMUD
AEBSH
AEKER
AENEX
AFFNX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AI.
AIEXJ
AIGVJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
ARUGR
ASPBG
AVWKF
AXJTR
AZFZN
BKOJK
BLXMC
CS3
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
G-Q
GBLVA
HMJ
HVGLF
HZ~
IHE
J1W
KOM
M26
M41
MHUIS
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
RNS
ROL
RPZ
SDF
SDG
SDP
SES
SEW
SME
SPC
SPCBC
SSW
SSZ
T5K
TN5
VH1
VOH
WH7
WUQ
XPP
ZMT
~02
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
ID FETCH-LOGICAL-c303t-30d6ce2f16a78f91fdca3aebb3972d147e14e9a0f4a55112b03f7e8d7c7dbbd3
ISICitedReferencesCount 9
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000615803400009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0168-9274
IngestDate Sat Nov 29 07:23:35 EST 2025
Tue Nov 18 22:40:48 EST 2025
Fri Feb 23 02:48:17 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Generalized eigenvalue problem
Exponential canonical correlation analysis (ECCA)
Randomized singular value decomposition (RSVD)
Canonical correlation analysis (CCA)
Matrix exponential
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c303t-30d6ce2f16a78f91fdca3aebb3972d147e14e9a0f4a55112b03f7e8d7c7dbbd3
PageCount 24
ParticipantIDs crossref_primary_10_1016_j_apnum_2020_09_013
crossref_citationtrail_10_1016_j_apnum_2020_09_013
elsevier_sciencedirect_doi_10_1016_j_apnum_2020_09_013
PublicationCentury 2000
PublicationDate June 2021
2021-06-00
PublicationDateYYYYMMDD 2021-06-01
PublicationDate_xml – month: 06
  year: 2021
  text: June 2021
PublicationDecade 2020
PublicationTitle Applied numerical mathematics
PublicationYear 2021
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Schell, Gardner (br0360) 1995; 43
Stewart (br0400) 1979; 23
Ahonen, Hadid, Pietikinen (br0020) 2006; 28
Avron, Boutsidis, Toledo, Zouzias (br0030) 2014; 36
Tao, Ip, Zhang, Shu (br0450) 2016; 54
Peng, Zhang, Zhang (br0320) 2010; 31
Sun (br0420) 1983; 41
Higham (br0210) 2008
Zhou (br0560) 2016
Martinsson, Rokhlin, Tygert (br0290) 2011; 30
Klami, Virtanen, Kaski (br0240) 2013; 14
Van Loan (br0490) 1977; 14
Fushiki (br0130) 2011; 21
Leurgans, Moyeed, Silverman (br0250) 1993; 3
Hotelling (br0220) 1936; 28
Sarkar, Chakraborty (br0350) 2015; 40
Stewart (br0410) 2001
Qadar, Seghouane (br0330) 2019; 66
Dunham, Kravetz (br0110) 1975; 43
Kimura, Kameoka, Sugiyama, Nakano, Maeda, Sakano, Ishiguro (br0230) 2010
Wang, Yan, Yang (br0510) 2014; 23
Bach, Jordan (br0040) 2002; 3
Zhang, Fang, Tang, Shang, Xu (br0550) 2010; 40
Wang, Zhang, Bai, Li (br0520) 2020
Guo, Bai (br0180) 2005; 23
Hardoon, Szedmak, Shawetaylor (br0200) 2004; 16
Gu (br0160) 2015; 37
Reunanen (br0340) 2003; 3
Peng, Zhang (br0310) 2008; 19
Halko, Martinsson, Tropp (br0190) 2010; 53
Cai, Tang (br0070) 2018; 98
Alam, Fukumizu (br0010) 2013
Brittany, Serdar (br0060) 2015; 22
Golub, Zha (br0150) 1995; vol. 69
Soneson, Lilljebjörn, Fioretos, Fontes (br0380) 2010; 11
Mineiro, Karampatziakis (br0300) 2014
Liberty, Woolfe, Martinsson, Rokhlin, Tygert (br0270) 2007; 104
Shen, Sun, Yuan (br0370) 2013
Vinod (br0500) 1976; 4
Worsley, Poline, Friston, Evans (br0530) 1997; 6
Ewerbring, Luk (br0120) 1989; 27
Lindsey, Webster, Halpern (br0280) 2010; 27
Cruz-Cano, Lee (br0100) 2014; 70
Golub, Van Loan (br0140) 2014
Tu, Burdick, Millican, Mcgown (br0460) 1989; 61
Björck, Golub (br0050) 1973; 27
Wu, Feng, Zhang, Yang (br0540) 2017; 66
Udell, Townsend (br0470) 2019; 1
Cover, Hart (br0090) 1967; 13
Sun (br0430) 2001
Guo, Wu (br0170) 2019
Chu, Liao, Ng, Zhang (br0080) 2013; 35
Sun, Ji, Ye (br0440) 2011; 33
Uurtio, Monteiro, Kandola, Shawe-Taylor, Fernandez-Reyes, Rousu (br0480) 2017; 50
Golub (10.1016/j.apnum.2020.09.013_br0150) 1995; vol. 69
Shen (10.1016/j.apnum.2020.09.013_br0370) 2013
Worsley (10.1016/j.apnum.2020.09.013_br0530) 1997; 6
Schell (10.1016/j.apnum.2020.09.013_br0360) 1995; 43
Cai (10.1016/j.apnum.2020.09.013_br0070) 2018; 98
Sarkar (10.1016/j.apnum.2020.09.013_br0350) 2015; 40
Reunanen (10.1016/j.apnum.2020.09.013_br0340) 2003; 3
Peng (10.1016/j.apnum.2020.09.013_br0310) 2008; 19
Soneson (10.1016/j.apnum.2020.09.013_br0380) 2010; 11
Zhang (10.1016/j.apnum.2020.09.013_br0550) 2010; 40
Sun (10.1016/j.apnum.2020.09.013_br0440) 2011; 33
Bach (10.1016/j.apnum.2020.09.013_br0040) 2002; 3
Zhou (10.1016/j.apnum.2020.09.013_br0560) 2016
Chu (10.1016/j.apnum.2020.09.013_br0080) 2013; 35
Wang (10.1016/j.apnum.2020.09.013_br0510) 2014; 23
Klami (10.1016/j.apnum.2020.09.013_br0240) 2013; 14
Kimura (10.1016/j.apnum.2020.09.013_br0230) 2010
Tu (10.1016/j.apnum.2020.09.013_br0460) 1989; 61
Avron (10.1016/j.apnum.2020.09.013_br0030) 2014; 36
Björck (10.1016/j.apnum.2020.09.013_br0050) 1973; 27
Van Loan (10.1016/j.apnum.2020.09.013_br0490) 1977; 14
Ahonen (10.1016/j.apnum.2020.09.013_br0020) 2006; 28
Guo (10.1016/j.apnum.2020.09.013_br0180) 2005; 23
Wang (10.1016/j.apnum.2020.09.013_br0520) 2020
Martinsson (10.1016/j.apnum.2020.09.013_br0290) 2011; 30
Fushiki (10.1016/j.apnum.2020.09.013_br0130) 2011; 21
Cruz-Cano (10.1016/j.apnum.2020.09.013_br0100) 2014; 70
Dunham (10.1016/j.apnum.2020.09.013_br0110) 1975; 43
Peng (10.1016/j.apnum.2020.09.013_br0320) 2010; 31
Gu (10.1016/j.apnum.2020.09.013_br0160) 2015; 37
Cover (10.1016/j.apnum.2020.09.013_br0090) 1967; 13
Sun (10.1016/j.apnum.2020.09.013_br0420) 1983; 41
Alam (10.1016/j.apnum.2020.09.013_br0010) 2013
Stewart (10.1016/j.apnum.2020.09.013_br0410) 2001
Higham (10.1016/j.apnum.2020.09.013_br0210) 2008
Qadar (10.1016/j.apnum.2020.09.013_br0330) 2019; 66
Tao (10.1016/j.apnum.2020.09.013_br0450) 2016; 54
Vinod (10.1016/j.apnum.2020.09.013_br0500) 1976; 4
Leurgans (10.1016/j.apnum.2020.09.013_br0250) 1993; 3
Lindsey (10.1016/j.apnum.2020.09.013_br0280) 2010; 27
Liberty (10.1016/j.apnum.2020.09.013_br0270) 2007; 104
Stewart (10.1016/j.apnum.2020.09.013_br0400) 1979; 23
Wu (10.1016/j.apnum.2020.09.013_br0540) 2017; 66
Sun (10.1016/j.apnum.2020.09.013_br0430) 2001
Hardoon (10.1016/j.apnum.2020.09.013_br0200) 2004; 16
Ewerbring (10.1016/j.apnum.2020.09.013_br0120) 1989; 27
Guo (10.1016/j.apnum.2020.09.013_br0170)
Mineiro (10.1016/j.apnum.2020.09.013_br0300)
Halko (10.1016/j.apnum.2020.09.013_br0190) 2010; 53
Udell (10.1016/j.apnum.2020.09.013_br0470) 2019; 1
Golub (10.1016/j.apnum.2020.09.013_br0140) 2014
Uurtio (10.1016/j.apnum.2020.09.013_br0480) 2017; 50
Hotelling (10.1016/j.apnum.2020.09.013_br0220) 1936; 28
Brittany (10.1016/j.apnum.2020.09.013_br0060) 2015; 22
References_xml – volume: 40
  start-page: 709
  year: 2015
  end-page: 719
  ident: br0350
  article-title: DNA pattern recognition using canonical correlation algorithm
  publication-title: J. Biosci.
– volume: 37
  start-page: A1139
  year: 2015
  end-page: A1173
  ident: br0160
  article-title: Subspace iteration randomization and singular value problems
  publication-title: SIAM J. Sci. Comput.
– volume: 16
  start-page: 2639
  year: 2004
  end-page: 2664
  ident: br0200
  article-title: Canonical correlation analysis: an overview with application to learning methods
  publication-title: Neural Comput.
– volume: 28
  start-page: 2037
  year: 2006
  end-page: 2041
  ident: br0020
  article-title: Face description with local binary patterns: application to face recognition
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 11
  start-page: 1
  year: 2010
  ident: br0380
  article-title: Integrative analysis of gene expression and copy number alterations using canonical correlation analysis
  publication-title: BMC Bioinform.
– volume: 23
  start-page: 69
  year: 1979
  end-page: 85
  ident: br0400
  article-title: Perturbation bounds for the definite generalized eigenvalue problem
  publication-title: Linear Algebra Appl.
– volume: 70
  start-page: 88
  year: 2014
  end-page: 100
  ident: br0100
  article-title: Fast regularized canonical correlation analysis
  publication-title: Comput. Stat. Data Anal.
– year: 2013
  ident: br0010
  article-title: Higher-order regularized kernel CCA
  publication-title: 12th International Conference on Machine Learning and Applications (ICMLA)
– volume: 41
  start-page: 321
  year: 1983
  end-page: 343
  ident: br0420
  article-title: The perturbation bounds for eigenspaces of a definite matrix-pair
  publication-title: Numer. Math.
– volume: 27
  start-page: 579
  year: 1973
  end-page: 594
  ident: br0050
  article-title: Numerical methods for computing angles between linear subspaces
  publication-title: Math. Comput.
– volume: 98
  start-page: 178
  year: 2018
  end-page: 191
  ident: br0070
  article-title: A new randomized Kaczmarz based kernel canonical correlation analysis algorithm with applications to information retrieval
  publication-title: Neural Netw.
– year: 2010
  ident: br0230
  article-title: SemiCCA: efficient semi-supervised learning of canonical correlations
  publication-title: Int. Conf. Pattern Recognit.
– volume: 1
  start-page: 144
  year: 2019
  end-page: 160
  ident: br0470
  article-title: Why are big data matrices approximately low rank?
  publication-title: SIAM J. Math. Data Sci.
– volume: 23
  start-page: 920
  year: 2014
  end-page: 930
  ident: br0510
  article-title: A general exponential framework for dimensionality reduction
  publication-title: IEEE Trans. Image Process.
– volume: 28
  start-page: 321
  year: 1936
  end-page: 377
  ident: br0220
  article-title: Relations between two sets of variates
  publication-title: Biometrika
– year: 2020
  ident: br0520
  article-title: Orthogonal canonical correlation analysis and applications
  publication-title: Optim. Methods Softw.
– volume: 6
  start-page: 305
  year: 1997
  end-page: 319
  ident: br0530
  article-title: Characterizing the response of PET and fMRI data using multivariate linear models
  publication-title: NeuroImage
– volume: 14
  start-page: 971
  year: 1977
  end-page: 981
  ident: br0490
  article-title: The sensitivity of the matrix exponential
  publication-title: SIAM J. Numer. Anal.
– year: 2008
  ident: br0210
  article-title: Functions of Matrices: Theory and Computation
– volume: 35
  start-page: 3050
  year: 2013
  end-page: 3065
  ident: br0080
  article-title: Sparse canonical correlation analysis: new formulation and algorithm
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 23
  start-page: 305
  year: 2005
  end-page: 320
  ident: br0180
  article-title: On the minimal nonnegative solution of nonsymmetric algebraic Riccati equation
  publication-title: J. Comput. Math.
– year: 2013
  ident: br0370
  article-title: Orthogonal canonical correlation analysis and its application in feature fusion
  publication-title: Proceedings of the 16th International Conference on Information Fusion
– volume: 66
  start-page: 3247
  year: 2019
  end-page: 3256
  ident: br0330
  article-title: A projection CCA method for effective fMRI data analysis
  publication-title: IEEE Trans. Biomed. Eng.
– year: 2019
  ident: br0170
  article-title: Canonical correlation analysis (CCA) based multi-view learning: an overview
– volume: 43
  start-page: 2898
  year: 1995
  end-page: 2908
  ident: br0360
  article-title: Programmable canonical correlation analysis: a flexible framework for blind adaptive spatial filtering
  publication-title: IEEE Trans. Signal Process.
– year: 2001
  ident: br0410
  article-title: Matrix Algorithms, Volume II: Eigensystems
– year: 2014
  ident: br0140
  article-title: Matrix Computations
– volume: 4
  start-page: 147
  year: 1976
  end-page: 166
  ident: br0500
  article-title: Canonical ridge and econometrics of joint production
  publication-title: J. Econom.
– volume: 50
  start-page: 1
  year: 2017
  end-page: 33
  ident: br0480
  article-title: A tutorial on canonical correlation methods
  publication-title: ACM Comput. Surv.
– volume: 27
  start-page: 37
  year: 1989
  end-page: 52
  ident: br0120
  article-title: Canonical correlations and generalized SVD: applications and new algorithms
  publication-title: J. Comput. Appl. Math.
– volume: 36
  start-page: 111
  year: 2014
  end-page: 131
  ident: br0030
  article-title: Efficient dimensionality reduction for canonical correlation analysis
  publication-title: SIAM J. Sci. Comput.
– volume: 3
  start-page: 725
  year: 1993
  end-page: 740
  ident: br0250
  article-title: Canonical correlation analysis when the data are curves
  publication-title: J. R. Stat. Soc. B
– volume: 30
  start-page: 47
  year: 2011
  end-page: 68
  ident: br0290
  article-title: A randomized algorithm for the decomposition of matrices
  publication-title: Appl. Comput. Harmon. Anal.
– volume: 54
  start-page: 22
  year: 2016
  end-page: 30
  ident: br0450
  article-title: Exploring canonical correlation analysis with subspace and structured sparsity for web image annotation
  publication-title: Image Vis. Comput.
– volume: 104
  start-page: 20167
  year: 2007
  end-page: 20172
  ident: br0270
  article-title: Randomized algorithms for the low-rank approximation of matrices
  publication-title: Proc. Natl. Acad. Sci. USA
– volume: 3
  start-page: 1
  year: 2002
  end-page: 48
  ident: br0040
  article-title: Kernel independent component analysis
  publication-title: J. Mach. Learn. Res.
– volume: 27
  start-page: 257
  year: 2010
  end-page: 264
  ident: br0280
  article-title: Canonical correlation as a discriminant tool in a periodontal problem
  publication-title: Biom. J.
– volume: 40
  start-page: 186
  year: 2010
  end-page: 197
  ident: br0550
  article-title: Generalized discriminant analysis: a matrix exponential approach
  publication-title: IEEE Trans. Syst. Man Cybern., Part B, Cybern.
– volume: 3
  start-page: 1371
  year: 2003
  end-page: 1382
  ident: br0340
  article-title: Overfitting in making comparisons between variable selection methods
  publication-title: J. Mach. Learn. Res.
– volume: 21
  start-page: 137
  year: 2011
  end-page: 146
  ident: br0130
  article-title: Estimation of prediction error by using K-fold cross-validation
  publication-title: Stat. Comput.
– volume: vol. 69
  year: 1995
  ident: br0150
  article-title: The canonical correlations of matrix pairs and their numerical computation
  publication-title: Linear Algebra for Signal Processing
– volume: 22
  start-page: 289
  year: 2015
  end-page: 299
  ident: br0060
  article-title: A canonical correlation analysis-based dynamic Bayesian network prior to infer gene regulatory networks from multiple types of biological data
  publication-title: J. Comput. Biol.
– volume: 13
  start-page: 21
  year: 1967
  end-page: 27
  ident: br0090
  article-title: Nearest neighbor pattern classification
  publication-title: IEEE Trans. Inf. Theory
– volume: 43
  start-page: 35
  year: 1975
  end-page: 42
  ident: br0110
  article-title: Canonical correlation analysis in a predictive system
  publication-title: J. Exp. Educ.
– volume: 53
  start-page: 217
  year: 2010
  end-page: 288
  ident: br0190
  article-title: Finding structure with randomness: probabilistic algorithms for constructing approximate matrix decompositions
  publication-title: SIAM Rev.
– year: 2014
  ident: br0300
  article-title: A randomized algorithm for CCA
– volume: 31
  start-page: 1
  year: 2010
  end-page: 15
  ident: br0320
  article-title: A new canonical correlation analysis algorithm with local discrimination
  publication-title: Neural Process. Lett.
– year: 2001
  ident: br0430
  article-title: Matrix Perturbation Analysis
– volume: 33
  start-page: 194
  year: 2011
  end-page: 200
  ident: br0440
  article-title: Canonical correlation analysis for multilabel classification: a least-squares formulation, extensions, and analysis
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– year: 2016
  ident: br0560
  article-title: Machine Learning
– volume: 61
  start-page: 2219
  year: 1989
  end-page: 2224
  ident: br0460
  article-title: Canonical correlation technique for rank estimation of excitation-emission matrixes
  publication-title: Anal. Chem.
– volume: 66
  start-page: 328
  year: 2017
  end-page: 341
  ident: br0540
  article-title: Inexact implementation using Krylov subspace methods for large scale exponential discriminant analysis with applications to high dimensionality reduction problems
  publication-title: Pattern Recognit.
– volume: 14
  start-page: 965
  year: 2013
  end-page: 1003
  ident: br0240
  article-title: Bayesian canonical correlation analysis
  publication-title: J. Mach. Learn. Res.
– volume: 19
  start-page: 2822
  year: 2008
  end-page: 2832
  ident: br0310
  article-title: A semi-supervised canonical correlation analysis algorithms
  publication-title: J. Softw.
– volume: 54
  start-page: 22
  year: 2016
  ident: 10.1016/j.apnum.2020.09.013_br0450
  article-title: Exploring canonical correlation analysis with subspace and structured sparsity for web image annotation
  publication-title: Image Vis. Comput.
  doi: 10.1016/j.imavis.2016.06.008
– volume: 43
  start-page: 2898
  year: 1995
  ident: 10.1016/j.apnum.2020.09.013_br0360
  article-title: Programmable canonical correlation analysis: a flexible framework for blind adaptive spatial filtering
  publication-title: IEEE Trans. Signal Process.
  doi: 10.1109/78.476433
– year: 2001
  ident: 10.1016/j.apnum.2020.09.013_br0430
– volume: 4
  start-page: 147
  year: 1976
  ident: 10.1016/j.apnum.2020.09.013_br0500
  article-title: Canonical ridge and econometrics of joint production
  publication-title: J. Econom.
  doi: 10.1016/0304-4076(76)90010-5
– volume: 22
  start-page: 289
  year: 2015
  ident: 10.1016/j.apnum.2020.09.013_br0060
  article-title: A canonical correlation analysis-based dynamic Bayesian network prior to infer gene regulatory networks from multiple types of biological data
  publication-title: J. Comput. Biol.
  doi: 10.1089/cmb.2014.0296
– volume: 35
  start-page: 3050
  year: 2013
  ident: 10.1016/j.apnum.2020.09.013_br0080
  article-title: Sparse canonical correlation analysis: new formulation and algorithm
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2013.104
– ident: 10.1016/j.apnum.2020.09.013_br0300
– year: 2013
  ident: 10.1016/j.apnum.2020.09.013_br0010
  article-title: Higher-order regularized kernel CCA
– volume: 23
  start-page: 305
  year: 2005
  ident: 10.1016/j.apnum.2020.09.013_br0180
  article-title: On the minimal nonnegative solution of nonsymmetric algebraic Riccati equation
  publication-title: J. Comput. Math.
– volume: 104
  start-page: 20167
  year: 2007
  ident: 10.1016/j.apnum.2020.09.013_br0270
  article-title: Randomized algorithms for the low-rank approximation of matrices
  publication-title: Proc. Natl. Acad. Sci. USA
  doi: 10.1073/pnas.0709640104
– volume: 23
  start-page: 69
  year: 1979
  ident: 10.1016/j.apnum.2020.09.013_br0400
  article-title: Perturbation bounds for the definite generalized eigenvalue problem
  publication-title: Linear Algebra Appl.
  doi: 10.1016/0024-3795(79)90094-6
– volume: 27
  start-page: 37
  year: 1989
  ident: 10.1016/j.apnum.2020.09.013_br0120
  article-title: Canonical correlations and generalized SVD: applications and new algorithms
  publication-title: J. Comput. Appl. Math.
  doi: 10.1016/0377-0427(89)90360-9
– year: 2001
  ident: 10.1016/j.apnum.2020.09.013_br0410
– year: 2013
  ident: 10.1016/j.apnum.2020.09.013_br0370
  article-title: Orthogonal canonical correlation analysis and its application in feature fusion
– volume: 37
  start-page: A1139
  year: 2015
  ident: 10.1016/j.apnum.2020.09.013_br0160
  article-title: Subspace iteration randomization and singular value problems
  publication-title: SIAM J. Sci. Comput.
  doi: 10.1137/130938700
– volume: 40
  start-page: 186
  year: 2010
  ident: 10.1016/j.apnum.2020.09.013_br0550
  article-title: Generalized discriminant analysis: a matrix exponential approach
  publication-title: IEEE Trans. Syst. Man Cybern., Part B, Cybern.
  doi: 10.1109/TSMCB.2009.2024759
– volume: 16
  start-page: 2639
  year: 2004
  ident: 10.1016/j.apnum.2020.09.013_br0200
  article-title: Canonical correlation analysis: an overview with application to learning methods
  publication-title: Neural Comput.
  doi: 10.1162/0899766042321814
– volume: 27
  start-page: 579
  year: 1973
  ident: 10.1016/j.apnum.2020.09.013_br0050
  article-title: Numerical methods for computing angles between linear subspaces
  publication-title: Math. Comput.
  doi: 10.1090/S0025-5718-1973-0348991-3
– volume: 11
  start-page: 1
  year: 2010
  ident: 10.1016/j.apnum.2020.09.013_br0380
  article-title: Integrative analysis of gene expression and copy number alterations using canonical correlation analysis
  publication-title: BMC Bioinform.
  doi: 10.1186/1471-2105-11-191
– volume: 13
  start-page: 21
  year: 1967
  ident: 10.1016/j.apnum.2020.09.013_br0090
  article-title: Nearest neighbor pattern classification
  publication-title: IEEE Trans. Inf. Theory
  doi: 10.1109/TIT.1967.1053964
– volume: 31
  start-page: 1
  year: 2010
  ident: 10.1016/j.apnum.2020.09.013_br0320
  article-title: A new canonical correlation analysis algorithm with local discrimination
  publication-title: Neural Process. Lett.
  doi: 10.1007/s11063-009-9123-3
– volume: 53
  start-page: 217
  year: 2010
  ident: 10.1016/j.apnum.2020.09.013_br0190
  article-title: Finding structure with randomness: probabilistic algorithms for constructing approximate matrix decompositions
  publication-title: SIAM Rev.
  doi: 10.1137/090771806
– volume: 21
  start-page: 137
  year: 2011
  ident: 10.1016/j.apnum.2020.09.013_br0130
  article-title: Estimation of prediction error by using K-fold cross-validation
  publication-title: Stat. Comput.
  doi: 10.1007/s11222-009-9153-8
– ident: 10.1016/j.apnum.2020.09.013_br0170
– volume: 66
  start-page: 3247
  year: 2019
  ident: 10.1016/j.apnum.2020.09.013_br0330
  article-title: A projection CCA method for effective fMRI data analysis
  publication-title: IEEE Trans. Biomed. Eng.
  doi: 10.1109/TBME.2019.2902876
– volume: 3
  start-page: 1371
  year: 2003
  ident: 10.1016/j.apnum.2020.09.013_br0340
  article-title: Overfitting in making comparisons between variable selection methods
  publication-title: J. Mach. Learn. Res.
– volume: vol. 69
  year: 1995
  ident: 10.1016/j.apnum.2020.09.013_br0150
  article-title: The canonical correlations of matrix pairs and their numerical computation
– volume: 36
  start-page: 111
  year: 2014
  ident: 10.1016/j.apnum.2020.09.013_br0030
  article-title: Efficient dimensionality reduction for canonical correlation analysis
  publication-title: SIAM J. Sci. Comput.
  doi: 10.1137/130919222
– volume: 19
  start-page: 2822
  year: 2008
  ident: 10.1016/j.apnum.2020.09.013_br0310
  article-title: A semi-supervised canonical correlation analysis algorithms
  publication-title: J. Softw.
  doi: 10.3724/SP.J.1001.2008.02822
– volume: 6
  start-page: 305
  year: 1997
  ident: 10.1016/j.apnum.2020.09.013_br0530
  article-title: Characterizing the response of PET and fMRI data using multivariate linear models
  publication-title: NeuroImage
  doi: 10.1006/nimg.1997.0294
– year: 2014
  ident: 10.1016/j.apnum.2020.09.013_br0140
– year: 2010
  ident: 10.1016/j.apnum.2020.09.013_br0230
  article-title: SemiCCA: efficient semi-supervised learning of canonical correlations
  publication-title: Int. Conf. Pattern Recognit.
– volume: 3
  start-page: 1
  year: 2002
  ident: 10.1016/j.apnum.2020.09.013_br0040
  article-title: Kernel independent component analysis
  publication-title: J. Mach. Learn. Res.
– volume: 1
  start-page: 144
  year: 2019
  ident: 10.1016/j.apnum.2020.09.013_br0470
  article-title: Why are big data matrices approximately low rank?
  publication-title: SIAM J. Math. Data Sci.
  doi: 10.1137/18M1183480
– volume: 3
  start-page: 725
  year: 1993
  ident: 10.1016/j.apnum.2020.09.013_br0250
  article-title: Canonical correlation analysis when the data are curves
  publication-title: J. R. Stat. Soc. B
  doi: 10.1111/j.2517-6161.1993.tb01936.x
– year: 2020
  ident: 10.1016/j.apnum.2020.09.013_br0520
  article-title: Orthogonal canonical correlation analysis and applications
  publication-title: Optim. Methods Softw.
  doi: 10.1080/10556788.2019.1700257
– volume: 98
  start-page: 178
  year: 2018
  ident: 10.1016/j.apnum.2020.09.013_br0070
  article-title: A new randomized Kaczmarz based kernel canonical correlation analysis algorithm with applications to information retrieval
  publication-title: Neural Netw.
  doi: 10.1016/j.neunet.2017.11.013
– volume: 14
  start-page: 965
  year: 2013
  ident: 10.1016/j.apnum.2020.09.013_br0240
  article-title: Bayesian canonical correlation analysis
  publication-title: J. Mach. Learn. Res.
– volume: 30
  start-page: 47
  year: 2011
  ident: 10.1016/j.apnum.2020.09.013_br0290
  article-title: A randomized algorithm for the decomposition of matrices
  publication-title: Appl. Comput. Harmon. Anal.
  doi: 10.1016/j.acha.2010.02.003
– volume: 43
  start-page: 35
  year: 1975
  ident: 10.1016/j.apnum.2020.09.013_br0110
  article-title: Canonical correlation analysis in a predictive system
  publication-title: J. Exp. Educ.
  doi: 10.1080/00220973.1975.10806349
– volume: 14
  start-page: 971
  year: 1977
  ident: 10.1016/j.apnum.2020.09.013_br0490
  article-title: The sensitivity of the matrix exponential
  publication-title: SIAM J. Numer. Anal.
  doi: 10.1137/0714065
– volume: 28
  start-page: 321
  year: 1936
  ident: 10.1016/j.apnum.2020.09.013_br0220
  article-title: Relations between two sets of variates
  publication-title: Biometrika
  doi: 10.1093/biomet/28.3-4.321
– volume: 28
  start-page: 2037
  year: 2006
  ident: 10.1016/j.apnum.2020.09.013_br0020
  article-title: Face description with local binary patterns: application to face recognition
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2006.244
– volume: 61
  start-page: 2219
  year: 1989
  ident: 10.1016/j.apnum.2020.09.013_br0460
  article-title: Canonical correlation technique for rank estimation of excitation-emission matrixes
  publication-title: Anal. Chem.
  doi: 10.1021/ac00194a020
– volume: 33
  start-page: 194
  year: 2011
  ident: 10.1016/j.apnum.2020.09.013_br0440
  article-title: Canonical correlation analysis for multilabel classification: a least-squares formulation, extensions, and analysis
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2010.160
– volume: 66
  start-page: 328
  year: 2017
  ident: 10.1016/j.apnum.2020.09.013_br0540
  article-title: Inexact implementation using Krylov subspace methods for large scale exponential discriminant analysis with applications to high dimensionality reduction problems
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2016.08.020
– volume: 70
  start-page: 88
  year: 2014
  ident: 10.1016/j.apnum.2020.09.013_br0100
  article-title: Fast regularized canonical correlation analysis
  publication-title: Comput. Stat. Data Anal.
  doi: 10.1016/j.csda.2013.09.020
– volume: 23
  start-page: 920
  year: 2014
  ident: 10.1016/j.apnum.2020.09.013_br0510
  article-title: A general exponential framework for dimensionality reduction
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2013.2297020
– volume: 40
  start-page: 709
  year: 2015
  ident: 10.1016/j.apnum.2020.09.013_br0350
  article-title: DNA pattern recognition using canonical correlation algorithm
  publication-title: J. Biosci.
  doi: 10.1007/s12038-015-9555-z
– volume: 50
  start-page: 1
  year: 2017
  ident: 10.1016/j.apnum.2020.09.013_br0480
  article-title: A tutorial on canonical correlation methods
  publication-title: ACM Comput. Surv.
  doi: 10.1145/3136624
– volume: 41
  start-page: 321
  year: 1983
  ident: 10.1016/j.apnum.2020.09.013_br0420
  article-title: The perturbation bounds for eigenspaces of a definite matrix-pair
  publication-title: Numer. Math.
  doi: 10.1007/BF01418329
– year: 2016
  ident: 10.1016/j.apnum.2020.09.013_br0560
– volume: 27
  start-page: 257
  year: 2010
  ident: 10.1016/j.apnum.2020.09.013_br0280
  article-title: Canonical correlation as a discriminant tool in a periodontal problem
  publication-title: Biom. J.
  doi: 10.1002/bimj.4710270303
– year: 2008
  ident: 10.1016/j.apnum.2020.09.013_br0210
SSID ssj0005540
Score 2.356284
Snippet Canonical correlation analysis (CCA) is a famous data analysis method that has been successfully used in many areas. CCA extracts meaningful information from a...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 101
SubjectTerms Canonical correlation analysis (CCA)
Exponential canonical correlation analysis (ECCA)
Generalized eigenvalue problem
Matrix exponential
Randomized singular value decomposition (RSVD)
Title A randomized exponential canonical correlation analysis method for data analysis and dimensionality reduction
URI https://dx.doi.org/10.1016/j.apnum.2020.09.013
Volume 164
WOSCitedRecordID wos000615803400009&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: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1873-5460
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0005540
  issn: 0168-9274
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1NT9swGLamssMuMMYmygbygVsJchInTo7VBNo4IA6V1lvk2I5URNMqbVG1X7_XH3HCh6px4BJV-XDdvk_tx28fPy9C52lKc1rRKkgYKQOaRiIouZJBIjPBmYxFKKkpNsFub7PpNL9zgsyVKSfA6jrbbvPlu4YazkGw9dbZN4TbNwon4DUEHY4Qdjj-V-DHI5h-5GI--wtcUm2Xi1oLgrQNCK8XtTMEaRonghvx1pXE1pI2skMtG-0u6NS61EUArIGHpu2NNnz1IW1NbB2hrTf2X6CH0dx7wnrm_mdjMvHcTZhaCmT0BNdq1k9ARD2hVJuTTGHMjGyxHT-oprQ3LIbufjvDhnbX9IvB2-YR7i_5EjoKS_eIGAtau1f1qVX2synMCwtbzdp9YRopdCMFyQuiCxvvRSzJswHaG_--mt50QqDEbJv1H6P1pjIqwBd9eZ2_9DjJ5DPad4sJPLYgOEQfVP0FHbg4YDdsr47QfIw7TOAeJrDHBO5hArehxxYTGDCBNSa6C9AafooJ7DHxFU2uryY_fwWuzkYggMCsg5hIXReuClPOsioPKyl4zFVZAleNZEiZCqnKOakoTzQ_L0lcMZVJJpgsSxl_QwPoqzpGWFJOiKJK8KyElTfPSEwlVZFKhAQenA9R1H55hXAe9LoUykOxI3BDdOEfWloLlt23p21UCsciLTssAGe7Hjx52_t8R5-6X8MPNFg3G3WKPorH9WzVnDmQ_QMUlptT
linkProvider Elsevier
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=A+randomized+exponential+canonical+correlation+analysis+method+for+data+analysis+and+dimensionality+reduction&rft.jtitle=Applied+numerical+mathematics&rft.au=Wu%2C+Gang&rft.au=Li%2C+Fei&rft.date=2021-06-01&rft.issn=0168-9274&rft.volume=164&rft.spage=101&rft.epage=124&rft_id=info:doi/10.1016%2Fj.apnum.2020.09.013&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_apnum_2020_09_013
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0168-9274&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0168-9274&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0168-9274&client=summon