Abstract
As an extension of the traditional principal component analysis, the multi-view canonical correlation analysis (MCCA) aims at reducing m high dimensional random variables \(\boldsymbol {s}_{i}\in \mathbb {R}^{n_{i}}~(i=1,2,\ldots ,m)\) by proper projection matrices \(X_{i}\in \mathbb {R}^{n_{i}\times \ell }\) so that the m reduced ones \(\boldsymbol {y}_{i}=X_{i}^{\mathrm {T}}\boldsymbol {s}_{i}\in \mathbb {R}^{\ell }\) have the “maximal correlation.” Various measures of the correlation for yi (i = 1,2,…,m) in MCCA have been proposed. One of the earliest criteria is the sum of all traces of pair-wise correlation matrices between yi and yj subject to the orthogonality constraints on Xi, i = 1,2,…,m. The resulting problem is to maximize a homogeneous quadratic function over the product of Stiefel manifolds and is referred to as the MAXBET problem. In this paper, the problem is first reformulated as a coupled nonlinear eigenvalue problem with eigenvector dependency (NEPv) and then solved by a novel self-consistent-field (SCF) iteration. Global and local convergences of the SCF iteration are studied and proven computational techniques in the standard eigenvalue problem are incorporated to yield more practical implementations. Besides the preliminary numerical evaluations on various types of synthetic problems, the efficiency of the SCF iteration is also demonstrated in an application to multi-view feature extraction for unsupervised learning.
Similar content being viewed by others
References
Absil, P.-A., Baker, C. G., Gallivan, K. A.: Trust-region methods on Riemannian manifolds. Found. Comput. Math. 7(3), 303–330 (2007)
Absil, P. -A., Mahony, R., Sepulchre, R.: Optimization Algorithms on Matrix Manifolds. Princeton University Press, Princeton (2008)
Bai, Z., Demmel, J. W., Dongarra, J., Ruhe, A., Vorst, H., Van Der Vorst, H.: Templates for the Solution of Algebraic Eigenvalue Problems: A Practical Guide. SIAM, Philadelphia (2000)
Bai, Z., Lu, D., Vandereycken, B.: Robust Rayleigh quotient minimization and nonlinear eigenvalue problems. SIAM J. Sci. Comput. 40, A3495–A3522 (2018)
Bendel, R. B., Mickey, M. R.: Population correlation matrices for sampling experiments. Comm Statist. Simul. Comput. 7(2), 163–182 (1978)
Ten Berge, J. M. F.: Generalized approaches to the MAXBET problem and the MAXDIFF problem, with applications to canonical correlations. Psychometrika 53(4), 487–494 (1988)
Ten Berge, J. M. F., Knol, D. L.: Orthogonal rotations to maximal agreement for two or more matrices of different column orders. Psychometrika 49 (4), 49–55 (1984)
Cai, Y., Zhang, L. -H., Bai, Z., Li, R. -C.: On an eigenvector-dependent nonlinear eigenvalue problem. SIAM J. Matrix Anal. Appl. 39(3), 1360–1382 (2018)
Chu, M. T., Watterson, J. L.: On a multivariate eigenvalue problem, Part I: Algebraic theory and a power method. SIAM J. Sci. Comput. 14(4), 1089–1106 (1993)
Cunningham, J. P., Ghahramani, Z.: Linear dimensionality reduction: Survey, insights, and generalizations. J. Mach. Lear. Res. 16, 2859–2900 (2015)
Davies, P. I., Higham, N. J.: Numerically stable generation of correlation matrices and their factors. BIT 40, 640–651 (2000)
Davis, C., Kahan, W.: The rotation of eigenvectors by a perturbation. III. SIAM J. Numer. Anal. 7, 1–46 (1970)
Van de Geer, J. P.: Linear relations among k sets of variables. Psychometrika 49, 70–94 (1984)
Goemans, M. X., Williamson, D. P.: Improved approximation algorithms for maximum cut and satisfiability problems using semidefinite programming. J. ACM 42, 1115–1145 (1995)
Golub, G. H., Van Loan, C. F.: Matrix Computations, 4th edn. Johns Hopkins University Press, Baltimore (2013)
Guan, Y., Chu, M. T., Chu, D.: SVD-based algorithms for the best rank-1 approximation of a symmetric tensor. SIAM J. Matrix Anal. Appl. 39, 1095–1115 (2018)
Hanafi, M., Ten Berge, J. M. F.: Global optimality of the successive Maxbet algorithm. Psychometrika 68, 97–103 (2003)
Hardoon, D. R., Szedmak, S., Shawe-Taylor, J.: Canonical correlation analysis: An overview with application to learning methods. Neural Comput. 16, 2639–2664 (2004)
Horst, P.: Relations among m sets of measures. Psychometrika 26, 129–149 (1961)
Hotelling, H.: Relations between two sets of variates. Biometrika 28, 321–377 (1936)
Kettenring, J. R.: Canonical analysis of several sets of variables. Biometrika 58(1), 433–451 (1971)
Knyazev, A. V.: Toward the optimal preconditioned eigensolver: Locally optimal block preconditioned conjugate gradient method. SIAM J. Sci. Comput. 23(2), 517–541 (2001)
Knyazev, A. V., Argentati, M. E.: Rayleigh-Ritz majorization error bounds with applications to FEM. SIAM J Matrix Anal Appl 31(3), 1521–1537 (2010)
Kovač-Striko, J., Veselić, K.: Some remarks on the spectra of Hermitian matrices. Linear Algebra Appl. 145, 221–229 (1991)
Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’06), pp. 2169–2178 (2006)
Li, F. F., Fergus, R., Perona, P.: Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories. Comput. Vis. Image Underst. 106, 59–70 (2007)
Li, R. -C.: New perturbation bounds for the unitary polar factor. SIAM J. Matrix Anal. Appl. 16, 327–332 (1995)
Li, R. -C.: Accuracy of computed eigenvectors via optimizing a Rayleigh quotient. BIT 44(3), 585–593 (2004)
Li, R.-C.: Rayleigh quotient based optimization methods for eigenvalue problems. In: Bai, Z., Gao, W., Su, Y. (eds.) Matrix Functions and Matrix Equations, volume 19 of Series in Contemporary Applied Mathematics, pp 76–108. World Scientific, Singapore (2015)
Li, Z., Nie, F., Chang, X., Yang, Y.: Beyond trace Weighted Harmonic mean of trace ratios for multiclass discriminant analysis. IEEE Trans. Knowl. Data Engrg. 29(10), 2100–2110 (2017)
Lingoes, J. C., Borg, I.: A direct approach to individual differences scaling using increasingly complex transformations. Psychometrika 43, 491–519 (1978)
Liu, X. -G., Wang, X. -F., Wang, W.-G.: Maximization of matrix trace function of product S,tiefel manifolds. SIAM J Matrix Anal. Appl. 36 (4), 1489–1506 (2015)
Martin, R. M.: Electronic structure: Basic theory and practical methods. Cambridge University Press, Cambridge (2004)
Moré, J. J., Sorensen, D. C.: Computing a trust region step. SIAM J. Sci. Statist. Comput. 4(3), 553–572 (1983)
Nielsen, A. A.: Multiset canonical correlations analysis and multispectral, truly multitemporal remote sensing data. IEEE Trans. Image Process. 11(3), 293–305 (2002)
Nocedal, J.: Numerical Optimization, 2nd edn. Springer, New York (2006)
Parlett, B. N.: The symmetric eigenvalue problem. SIAM. Philadelphia (1998)
Pourahmadi, M., Wang, X.: Distribution of random correlation matrices: Hyperspherical parameterization of the Cholesky factor. Statist. Probab. Lett. 106(3), 5–12 (2015)
Saad, Y., Chelikowsky, J. R., Shontz, S. M.: Numerical methods for electronic structure calculations of materials. SIAM Rev. 52(1), 3–54 (2010)
Seber, G. A. F.: A Matrix Handbook for Statisticians. Wiley, New Jersey (2007)
Stewart, G. W.: Matrix Algorithms, Vol. II: Eigensystems. SIAM, Philadelphia (2001)
Veleva, E.: Generation of correlation matrices. AIP Conf. Proc. 1895(120008), 1–7 (2017)
von Neumann, J.: Some matrix-inequalities and metrization of matrix- space. Tomck. Univ Some Rev. 1, 286–300 (1937)
Wang, L., Li, R.-C.: A scalable algorithm for large-scale unsupervised multi-view partial least squares. IEEE Trans. Big Data. https://doi.org/10.1109/TBDATA.2020.3014937, to appear (2020)
Wang, L., Zhang, L. -H., Bai, Z., Li, R. -C.: Orthogonal canonical correlation analysis and applications. Optim. Methods Softw. 35(4), 787–807 (2020)
Wang, Z., Ruan, Q., An, G.: Projection-optimal local Fisher discriminant analysis for feature extraction. Neural Comput. Appl. 26, 589–601 (2015)
Yang, W. H., Zhang, L. -H., Song, R. Y.: Optimality conditions of the nonlinear programming on Riemannian, manifolds. Pac. J. Optim. 10, 415–434 (2014)
Yang, X., Liu, W., Liu, W., Tao, D.: A survey on canonical correlation analysis. IEEE Trans. Knowl. Data Engrg. 33(6), 2349–2368 (2020)
Yu, Y., Zhang, L. -H., Zhang, S.: Simultaneous clustering of multiview biomedical data using manifold optimization. Bioinformatics 35(20), 4029–4037 (2019)
Zhang, L. -H.: Riemannian Newton method for the multivariate eigenvalue problem. SIAM J. Matrix Anal. Appl. 31(5), 2972–2996 (2010)
Zhang, L.-H.: Riemannian trust-region method for the maximal correlation problem. Numer. Funct. Anal. Optim. 33(3), 338–362 (2012)
Zhang, L. -H., Li, R.-C.: Maximization of the sum of the trace ratio on the Stiefel, manifold, I Theory. Sci. China Math. 57(12), 2495–2508 (2014)
Zhang, L. -H., Li, R.-C.: Maximization of the sum of the trace ratio on the Stiefel manifold, II Computation. Sci. China Math. 58, 1549–1566 (2015)
Zhang, L. -H., Ma, X., Shen, C.: A structure-exploiting nested Lanczos-type iteration for the multi-view canonical correlation analysis. SIAM J. Sci. Comput. 43(4), A2685–A2713 (2021)
Zhang, L. -H., Li, Wang, Bai, Z., Li, R.-C.: A self-consistent-field iteration for orthogonal canonical correlation analysis. IEEE Trans. Pattern Anal. Mach Intell. 44(2), 890–904 (2022)
Zhang, L. -H., Yang, W. H., Shen, C., Ying, J.: An eigenvalue-based method for the unbalanced Procrustes problem. SIAM J Matrix Anal. Appl. 41(3), 957–983 (2020)
Acknowledgements
The authors are grateful to the anonymous referees for their useful comments and suggestions to improve the presentation of this paper.
Funding
The work of the third author was supported partially by NSF DMS-2009689 and NIH R01AG075582; the work of the fourth author was supported partially by the National Natural Science Foundation of China NSFC-12071332; and the work of the fifth author was supported partially by NSF DMS-1719620 and DMS-2009689.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Additional information
Communicated by: Raymond H. Chan
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Ma, X., Shen, C., Wang, L. et al. A self-consistent-field iteration for MAXBET with an application to multi-view feature extraction. Adv Comput Math 48, 13 (2022). https://doi.org/10.1007/s10444-022-09929-3
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10444-022-09929-3
Keywords
- MAXBET
- Multi-view canonical correlation analysis
- Multi-view feature extraction
- Nonlinear eigenvalue problem
- Self-consistent-field iteration
- Stiefel manifold