Consistency of Kernel Canonical Correlation Analysis
Kenji Fukumizu, Francis Bach and Arthur Gretton
Institute of Statistical Mathematics, Tokyo, Japan.
While kernel CCA has been applied in many problems, the convergence of the estimated function with finite sample to the true function has not been established yet. This paper gives a mathematical proof of the statistical convergence of kernel CCA and a related method (NOCCO) to provide a theoretical justification for the methods. The result gives also a sufficient condition on the regularisation coefficient in the methods to ensure convergence.