Regularised Least-Squares Regression with Infinite-Dimensional Output Space
Machine Learning
2022-02-17 v7 Machine Learning
Abstract
This short technical report presents some learning theory results on vector-valued reproducing kernel Hilbert space (RKHS) regression, where the input space is allowed to be non-compact and the output space is a (possibly infinite-dimensional) Hilbert space. Our approach is based on the integral operator technique using spectral theory for non-compact operators. We place a particular emphasis on obtaining results with as few assumptions as possible; as such we only use Chebyshev's inequality, and no effort is made to obtain the best rates or constants.
Keywords
Cite
@article{arxiv.2010.10973,
title = {Regularised Least-Squares Regression with Infinite-Dimensional Output Space},
author = {Junhyunng Park and Krikamol Muandet},
journal= {arXiv preprint arXiv:2010.10973},
year = {2022}
}