English

An RKHS formulation of the inverse regression dimension-reduction problem

Statistics Theory 2009-04-02 v1 Statistics Theory

Abstract

Suppose that YY is a scalar and XX is a second-order stochastic process, where YY and XX are conditionally independent given the random variables ξ1,...,ξp\xi_1,...,\xi_p which belong to the closed span LX2L_X^2 of XX. This paper investigates a unified framework for the inverse regression dimension-reduction problem. It is found that the identification of LX2L_X^2 with the reproducing kernel Hilbert space of XX provides a platform for a seamless extension from the finite- to infinite-dimensional settings. It also facilitates convenient computational algorithms that can be applied to a variety of models.

Keywords

Cite

@article{arxiv.0904.0076,
  title  = {An RKHS formulation of the inverse regression dimension-reduction problem},
  author = {Tailen Hsing and Haobo Ren},
  journal= {arXiv preprint arXiv:0904.0076},
  year   = {2009}
}

Comments

Published in at http://dx.doi.org/10.1214/07-AOS589 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)

R2 v1 2026-06-21T12:46:55.664Z