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.
| Author(s): | Fukumizu, K. and Bach, F. and Gretton, A. |
| Book Title: | Advances in neural information processing systems 18 |
| Journal: | Advances in Neural Information Processing Systems 18: Proceedings of the 2005 Conference |
| Pages: | 387-394 |
| Year: | 2006 |
| Month: | May |
| Day: | 0 |
| Editors: | Weiss, Y. , B. Sch{\"o}lkopf, J. Platt |
| Publisher: | MIT Press |
| Bibtex Type: | Conference Paper (inproceedings) |
| Address: | Cambridge, MA, USA |
| Event Name: | Nineteenth Annual Conference on Neural Information Processing Systems (NIPS 2005) |
| Event Place: | Vancouver, BC, Canada |
| Digital: | 0 |
| Electronic Archiving: | grant_archive |
| ISBN: | 0-262-23253-7 |
| Language: | en |
| Organization: | Max-Planck-Gesellschaft |
| School: | Biologische Kybernetik |
| Links: | |
BibTex
@inproceedings{3775,
title = {Statistical Convergence of Kernel CCA},
journal = {Advances in Neural Information Processing Systems 18: Proceedings of the 2005 Conference},
booktitle = {Advances in neural information processing systems 18},
abstract = {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.},
pages = {387-394},
editors = {Weiss, Y. , B. Sch{\"o}lkopf, J. Platt},
publisher = {MIT Press},
organization = {Max-Planck-Gesellschaft},
school = {Biologische Kybernetik},
address = {Cambridge, MA, USA},
month = may,
year = {2006},
slug = {3775},
author = {Fukumizu, K. and Bach, F. and Gretton, A.},
month_numeric = {5}
}