Saved in:
Bibliographic Details
Main Authors: Ni, Yijin, Yu, Chuanping, Ko, Andy, Huo, Xiaoming
Format: Preprint
Published: 2019
Subjects:
Online Access:https://arxiv.org/abs/1903.00037
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914979143221248
author Ni, Yijin
Yu, Chuanping
Ko, Andy
Huo, Xiaoming
author_facet Ni, Yijin
Yu, Chuanping
Ko, Andy
Huo, Xiaoming
contents This paper introduces a method called Sequential and Simultaneous Distance-based Dimension Reduction ($S^2D^2R$) that performs simultaneous dimension reduction for a pair of random vectors based on Distance Covariance (dCov). Compared with Sufficient Dimension Reduction (SDR) and Canonical Correlation Analysis (CCA)-based approaches, $S^2D^2R$ is a model-free approach that does not impose dimensional or distributional restrictions on variables and is more sensitive to nonlinear relationships. Theoretically, we establish a non-asymptotic error bound to guarantee the performance of $S^2D^2R$. Numerically, $S^2D^2R$ performs comparable to or better than other state-of-the-art algorithms and is computationally faster. All codes of our $S^2D^2R$ method can be found on Github, including an R package named S2D2R.
format Preprint
id arxiv_https___arxiv_org_abs_1903_00037
institution arXiv
publishDate 2019
record_format arxiv
spellingShingle Sequential and Simultaneous Distance-based Dimension Reduction
Ni, Yijin
Yu, Chuanping
Ko, Andy
Huo, Xiaoming
Methodology
This paper introduces a method called Sequential and Simultaneous Distance-based Dimension Reduction ($S^2D^2R$) that performs simultaneous dimension reduction for a pair of random vectors based on Distance Covariance (dCov). Compared with Sufficient Dimension Reduction (SDR) and Canonical Correlation Analysis (CCA)-based approaches, $S^2D^2R$ is a model-free approach that does not impose dimensional or distributional restrictions on variables and is more sensitive to nonlinear relationships. Theoretically, we establish a non-asymptotic error bound to guarantee the performance of $S^2D^2R$. Numerically, $S^2D^2R$ performs comparable to or better than other state-of-the-art algorithms and is computationally faster. All codes of our $S^2D^2R$ method can be found on Github, including an R package named S2D2R.
title Sequential and Simultaneous Distance-based Dimension Reduction
topic Methodology
url https://arxiv.org/abs/1903.00037