A Jacobi-Davidson Method for Large Scale Canonical Correlation Analysis

被引：0

作者：

Teng, Zhongming ^{[1
]}

Zhang, Xiaowei ^{[1
]}

机构：

[1] Fujian Agr & Forestry Univ, Coll Comp & Informat Sci, Fuzhou 350002, Peoples R China

来源：

ALGORITHMS | 2020年 / 13卷 / 09期

基金：

中国国家自然科学基金;

关键词：

canonical correlation analysis; Jacobi-Davidson; generalized eigenvalue problems; convergence; ALGORITHMS; CHEBYSHEV;

D O I：

10.3390/a13090229

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In the large scale canonical correlation analysis arising from multi-view learning applications, one needs to compute canonical weight vectors corresponding to a few of largest canonical correlations. For such a task, we propose a Jacobi-Davidson type algorithm to calculate canonical weight vectors by transforming it into the so-called canonical correlation generalized eigenvalue problem. Convergence results are established and reveal the accuracy of the approximate canonical weight vectors. Numerical examples are presented to support the effectiveness of the proposed method.

引用

页数：17

共 42 条

[1]

Allen-Zhu Z, 2017, PR MACH LEARN RES, V70

[2]

[Anonymous], 1976, Journal of Econometrics, DOI DOI 10.1016/0304-4076(76)90010-5

[3]

[Anonymous], 1965, J. Soc. Ind. Appl. Math., Ser. B Numer. Anal., DOI 10.1137/0702016

[4] A Jacobi-Davidson method for solving complex symmetric eigenvalue problems [J].

Arbenz, P ;

Hochstenbach, ME .

SIAM JOURNAL ON SCIENTIFIC COMPUTING, 2004, 25 (05) :1655-1673

[5] Minimization principles and computation for the generalized linear response eigenvalue problem [J].

Bai, Zhaojun ;

Li, Ren-Cang .

BIT NUMERICAL MATHEMATICS, 2014, 54 (01) :31-54

[6] A Jacobi-Davidson-type projection method for nonlinear eigenvalue problems [J].

Betcke, T ;

Voss, H .

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2004, 20 (03) :363-372

[7] A polynomial Jacobi-Davidson solver with support for non-monomial bases and deflation [J].

Campos, Carmen ;

Roman, Jose E. .

BIT NUMERICAL MATHEMATICS, 2020, 60 (02) :295-318

[8] Fast regularized canonical correlation analysis [J].

Cruz-Cano, Raul ;

Lee, Mei-Ling Ting .

COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2014, 70 :88-100

[9]

Demmel J. W., 1997, Applied numerical linear algebra, V56

[10] Algorithms for two dimensional multi set canonical correlation analysis [J].

Desai, Nandakishor ;

Seghouane, Abd-Krim ;

Palaniswami, Marimuthu .

PATTERN RECOGNITION LETTERS, 2018, 111 :101-108

← 1 2 3 4 5 →