Minimax convergence rates for kernel CCA
Minimax convergence rates for kernel CCA
复制标题
DOI:
10.1016/j.jmva.2016.05.008
复制
发表时间:
2016-09
期刊:
影响因子:
--
通讯作者:
Zengyan Fan;H. Lian
中科院分区:
文献类型:
--
作者:
Zengyan Fan;H. Lian
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.