The maximum separation subspace in sufficient dimension reduction with categorical response

Xin Zhang; Qing Mai; Hui Zou

The maximum separation subspace in sufficient dimension reduction with categorical response

Xin Zhang, Qing Mai, Hui Zou

Statistics (Twin Cities)

Research output: Contribution to journal › Article › peer-review

6 Scopus citations

Abstract

Sufficient dimension reduction (SDR) is a very useful concept for exploratory analysis and data visualization in regression, especially when the number of covariates is large. Many SDR methods have been proposed for regression with a continuous response, where the central subspace (CS) is the target of estimation. Various conditions, such as the linearity condition and the constant covariance condition, are imposed so that these methods can estimate at least a portion of the CS. In this paper we study SDR for regression and discriminant analysis with categorical response. Motivated by the exploratory analysis and data visualization aspects of SDR, we propose a new geometric framework to reformulate the SDR problem in terms of manifold optimization and introduce a new concept called Maximum Separation Subspace (MASES). The MASES naturally preserves the “sufficiency” in SDR without imposing additional conditions on the predictor distribution, and directly inspires a semi-parametric estimator. Numerical studies show MASES exhibits superior performance as compared with competing SDR methods in specific settings.

Original language	English (US)
Journal	Journal of Machine Learning Research
Volume	21
State	Published - Jan 1 2020

Bibliographical note

Funding Information:
We thank the Action Editor and three reviewers for constructive comments that have led to significant improvements of this paper. We would like to acknowledge support for this project from the National Science Foundation (NSF grant DMS-1613154 (Zhang), CCF-1617691 and CCF-1908969 (Mai and Zhang), DMS-1505111 (Zou)). We would like to thank Dr. Andreas Artemiou from the Cardiff University for sending us the R code for the linear PSVM method; and thank Dr. Liping Zhu from the Renmin University of China for his constructive comments and suggestions on the research.

Publisher Copyright:
© 2020 Xin Zhang, Qing Mai, Hui Zou. License: CC-BY 4.0, see https://creativecommons.org/licenses/by/4.0/. Attribution requirements are provided at http://jmlr.org/papers/v21/17-788.html.

Keywords

Categorical data analysis
Hellinger distance
Semi-parametric
Single index models
Sliced inverse regression
Sufficient dimension reduction

OpenUrl availability

Full text

Cite this

@article{27553c0464924b97800049f5c4ae8606,

title = "The maximum separation subspace in sufficient dimension reduction with categorical response",

abstract = "Sufficient dimension reduction (SDR) is a very useful concept for exploratory analysis and data visualization in regression, especially when the number of covariates is large. Many SDR methods have been proposed for regression with a continuous response, where the central subspace (CS) is the target of estimation. Various conditions, such as the linearity condition and the constant covariance condition, are imposed so that these methods can estimate at least a portion of the CS. In this paper we study SDR for regression and discriminant analysis with categorical response. Motivated by the exploratory analysis and data visualization aspects of SDR, we propose a new geometric framework to reformulate the SDR problem in terms of manifold optimization and introduce a new concept called Maximum Separation Subspace (MASES). The MASES naturally preserves the “sufficiency” in SDR without imposing additional conditions on the predictor distribution, and directly inspires a semi-parametric estimator. Numerical studies show MASES exhibits superior performance as compared with competing SDR methods in specific settings.",

keywords = "Categorical data analysis, Hellinger distance, Semi-parametric, Single index models, Sliced inverse regression, Sufficient dimension reduction",

author = "Xin Zhang and Qing Mai and Hui Zou",

note = "Funding Information: We thank the Action Editor and three reviewers for constructive comments that have led to significant improvements of this paper. We would like to acknowledge support for this project from the National Science Foundation (NSF grant DMS-1613154 (Zhang), CCF-1617691 and CCF-1908969 (Mai and Zhang), DMS-1505111 (Zou)). We would like to thank Dr. Andreas Artemiou from the Cardiff University for sending us the R code for the linear PSVM method; and thank Dr. Liping Zhu from the Renmin University of China for his constructive comments and suggestions on the research. Publisher Copyright: {\textcopyright} 2020 Xin Zhang, Qing Mai, Hui Zou. License: CC-BY 4.0, see https://creativecommons.org/licenses/by/4.0/. Attribution requirements are provided at http://jmlr.org/papers/v21/17-788.html.",

year = "2020",

month = jan,

day = "1",

language = "English (US)",

volume = "21",

journal = "Journal of Machine Learning Research",

issn = "1532-4435",

publisher = "Microtome Publishing",

}

TY - JOUR

T1 - The maximum separation subspace in sufficient dimension reduction with categorical response

AU - Zhang, Xin

AU - Mai, Qing

AU - Zou, Hui

N1 - Funding Information: We thank the Action Editor and three reviewers for constructive comments that have led to significant improvements of this paper. We would like to acknowledge support for this project from the National Science Foundation (NSF grant DMS-1613154 (Zhang), CCF-1617691 and CCF-1908969 (Mai and Zhang), DMS-1505111 (Zou)). We would like to thank Dr. Andreas Artemiou from the Cardiff University for sending us the R code for the linear PSVM method; and thank Dr. Liping Zhu from the Renmin University of China for his constructive comments and suggestions on the research. Publisher Copyright: © 2020 Xin Zhang, Qing Mai, Hui Zou. License: CC-BY 4.0, see https://creativecommons.org/licenses/by/4.0/. Attribution requirements are provided at http://jmlr.org/papers/v21/17-788.html.

PY - 2020/1/1

Y1 - 2020/1/1

N2 - Sufficient dimension reduction (SDR) is a very useful concept for exploratory analysis and data visualization in regression, especially when the number of covariates is large. Many SDR methods have been proposed for regression with a continuous response, where the central subspace (CS) is the target of estimation. Various conditions, such as the linearity condition and the constant covariance condition, are imposed so that these methods can estimate at least a portion of the CS. In this paper we study SDR for regression and discriminant analysis with categorical response. Motivated by the exploratory analysis and data visualization aspects of SDR, we propose a new geometric framework to reformulate the SDR problem in terms of manifold optimization and introduce a new concept called Maximum Separation Subspace (MASES). The MASES naturally preserves the “sufficiency” in SDR without imposing additional conditions on the predictor distribution, and directly inspires a semi-parametric estimator. Numerical studies show MASES exhibits superior performance as compared with competing SDR methods in specific settings.

AB - Sufficient dimension reduction (SDR) is a very useful concept for exploratory analysis and data visualization in regression, especially when the number of covariates is large. Many SDR methods have been proposed for regression with a continuous response, where the central subspace (CS) is the target of estimation. Various conditions, such as the linearity condition and the constant covariance condition, are imposed so that these methods can estimate at least a portion of the CS. In this paper we study SDR for regression and discriminant analysis with categorical response. Motivated by the exploratory analysis and data visualization aspects of SDR, we propose a new geometric framework to reformulate the SDR problem in terms of manifold optimization and introduce a new concept called Maximum Separation Subspace (MASES). The MASES naturally preserves the “sufficiency” in SDR without imposing additional conditions on the predictor distribution, and directly inspires a semi-parametric estimator. Numerical studies show MASES exhibits superior performance as compared with competing SDR methods in specific settings.

KW - Categorical data analysis

KW - Hellinger distance

KW - Semi-parametric

KW - Single index models

KW - Sliced inverse regression

KW - Sufficient dimension reduction

UR - http://www.scopus.com/inward/record.url?scp=85086800575&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85086800575&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85086800575

SN - 1532-4435

VL - 21

JO - Journal of Machine Learning Research

JF - Journal of Machine Learning Research

ER -

The maximum separation subspace in sufficient dimension reduction with categorical response

Abstract

Bibliographical note

Keywords

OpenUrl availability

Other files and links

Fingerprint

Cite this