| Article ID | Journal | Published Year | Pages | File Type |
|---|---|---|---|---|
| 1145161 | Journal of Multivariate Analysis | 2016 | 8 Pages |
Abstract
Consistency of kernel canonical correlation analysis (kernel CCA) has been established while its optimal convergence rate remains unknown. In this paper we derive rigorous upper and lower bounds for the convergence rate of the weight functions in kernel CCA. In particular the optimal convergence rate is shown to only depend on the rate of decay of the eigenvalues of the covariance operators.
Keywords
Related Topics
Physical Sciences and Engineering
Mathematics
Numerical Analysis
Authors
Zengyan Fan, Heng Lian,