Statistical Convergence of Kernel CCA
K Fukumizu, F Bach and Arthur Gretton
In: NIPS 2005, Dec. 5 - Dec. 10, Vancouver, Canada.
While kernel canonical correlation analysis (kernel CCA) has been
applied in many problems, the asymptotic convergence of the functions
estimated from a finite sample to the true functions has not yet been established. This paper gives a rigorous proof of the statistical
convergence of kernel CCA and a related method (NOCCO),
which provides a theoretical justification for these methods. The
result also gives a sufficient condition on the decay of the regularization
coefficient in the methods to ensure convergence.