Skip to main content
SpringerLink
Log in

Towards the global solution of the maximal correlation problem

  • Published:
Journal of Global Optimization Aims and scope Submit manuscript

Abstract

The maximal correlation problem (MCP) aiming at optimizing correlation between sets of variables plays a very important role in many areas of statistical applications. Currently, algorithms for the general MCP stop at solutions of the multivariate eigenvalue problem for a related matrix A, which serves as a necessary condition for the global solutions of the MCP. However, the reliability of the statistical prediction in applications relies greatly on the global maximizer of the MCP, and would be significantly impacted if the solution found is a local maximizer. Towards the global solution of the MCP, we have obtained four results in the present paper. First, the sufficient and necessary condition for global optimality of the MCP when A is a positive matrix is extended to the nonnegative case. Secondly, the uniqueness of the multivariate eigenvalues in the global maxima of the MCP is proved either when there are only two sets of variables involved, or when A is nonnegative. The uniqueness of the global maximizer of the MCP for the nonnegative irreducible case is also proved. These theoretical achievements lead to our third result that if A is a nonnegative irreducible matrix, both the Horst-Jacobi algorithm and the Gauss-Seidel algorithm converge globally to the global maximizer of the MCP. Lastly, some new estimates of the multivariate eigenvalues related to the global maxima are obtained.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Bhatia R.: Positive Definite Matrices. Princeton University Press, Princeton (2007)

    Google Scholar 

  2. Chu M.T., Watterson J.L.: On a multivariate eigenvalue problem: I. Algebraic theory and power method. SIAM J. Sci. Comput. 14, 1089–1106 (1993)

    Article  Google Scholar 

  3. Golub G.H., Liao L.-Z.: Continuous methods for extreme and interior eigenvalue problems. Linear Algebra Appl. 415, 31–51 (2006)

    Article  Google Scholar 

  4. Golub G.H., Van Loan C.F.: Matrix Computations. 3rd edn. Johns Hopkins University Press, Baltimore, MD (1996)

    Google Scholar 

  5. Hanafi M., Ten Berge J.M.F.: Global optimality of the successive Maxbet algorithm. Psychometrika 68, 97–103 (2003)

    Article  Google Scholar 

  6. Horst P.: Relations among m sets of measures. Psychometrika 26, 129–149 (1961)

    Article  Google Scholar 

  7. Horst P.: Factor Analysis of Data Matrices. Holt Rinehart and Winston, New York (1965)

    Google Scholar 

  8. Hotelling H.: The most predictable criterion. J. Educ. Pyschol. 26, 139–142 (1935)

    Article  Google Scholar 

  9. Hotelling H.: Relations between two sets of variates. Biometrika 28, 321–377 (1936)

    Google Scholar 

  10. Kettenring J.R.: Canonical analysis of several sets of variables. Biometrika 58, 433–451 (1971)

    Article  Google Scholar 

  11. Meyer C.D.: Matrix Analysis and Applied Linear Algebra. SIAM, Philadelphia (2000)

    Google Scholar 

  12. Nocedal J., Wright S.J.: Numerical Optimization, Springer Series in Operations Research. 2nd edn. Springer, New York (2006)

    Google Scholar 

  13. Rao C.R., Rao M.B.: Matrix Algebra and its Applications to Statistics and Econometrics. World Scientific, River Edge (1998)

    Google Scholar 

  14. Sigg, C., Fischer, B., Ommer, B., Roth, V., Buhmann, J.: Nonnegative CCA for audiovisual source separation. In: IEEE International Workshop on Machine Learning for Signal Processing’07, IEEE, 2007

  15. Ten Berge J.M.F.: Generalized approaches to the MAXBET problem and the MAXDIFF problem, with applications to canonical correlations. Psychometrika 53, 487–494 (1988)

    Article  Google Scholar 

  16. Timm N.H.: Applied Multivariate Analysis. Springer, New York (2002)

    Google Scholar 

  17. Van de Geer J.R.: Linear relations among k sets of variables. Psychometrika 49, 79–94 (1984)

    Article  Google Scholar 

  18. Van Noorden, T.L., Barkmeijer, J.: The Multivariate Eigenvalue Problem: A New Application, Theory and a Subspace Accelerated Power Method. Universiteit Utrecht, preprint (2008)

  19. Zhang, L.-H., Chu, M.T.: Computing absolute maximum correlation, in preprint. Available: http://www4.ncsu.edu/~mtchu/Research/Papers/Readme.html

Download references

Author information

Authors and Affiliations

  1. Department of Applied Mathematics, Shanghai University of Finance and Economics, 777 Guoding Road, 200433, Shanghai, People’s Republic of China

    Lei-Hong Zhang

  2. Department of Mathematics, Hong Kong Baptist University, Kowloon Tong, Kowloon, Hong Kong, People’s Republic of China

    Li-Zhi Liao & Li-Ming Sun

Authors
  1. Lei-Hong Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Li-Zhi Liao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Li-Ming Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Li-Zhi Liao.

Additional information

This research was supported in part by grants from Hong Kong Baptist University (FRG) and the Research Grant Council of Hong Kong.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Zhang, LH., Liao, LZ. & Sun, LM. Towards the global solution of the maximal correlation problem. J Glob Optim 49, 91–107 (2011). https://doi.org/10.1007/s10898-010-9536-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10898-010-9536-6

Keywords

Search

Navigation