Minimax convergence rates for kernel CCA

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

4 Scopus Citations
View graph of relations

Author(s)

Detail(s)

Original languageEnglish
Pages (from-to)183-190
Journal / PublicationJournal of Multivariate Analysis
Volume150
Publication statusPublished - 1 Sept 2016
Externally publishedYes

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.

Research Area(s)

  • Canonical correlation analysis, Covariance operator, Cross-covariance operator, Lower bound

Citation Format(s)

Minimax convergence rates for kernel CCA. / Fan, Zengyan; Lian, Heng.
In: Journal of Multivariate Analysis, Vol. 150, 01.09.2016, p. 183-190.

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review