PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Consistency of Kernel Canonical Correlation Analysis
Kenji Fukumizu, Francis Bach and Arthur Gretton
(2005) Technical Report. Institute of Statistical Mathematics, Tokyo, Japan.

Abstract

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.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Monograph (Technical Report)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Theory & Algorithms
ID Code:1701
Deposited By:Arthur Gretton
Deposited On:28 November 2005