High-dimensional sign-constrained feature selection and grouping

Qin, S; Ding, H; Wu, Y; Liu, F

High-dimensional sign-constrained feature selection and grouping

Qin, S Ding, H Wu, Y Liu, F

Permalink

Publisher:: Springer Science and Business Media LLC
Publication Type:: Journal Article
Citation:: Annals of the Institute of Statistical Mathematics, 2020, pp. 1-33
Issue Date:: 2020-01-01

Closed Access

	Filename	Description	Size
	Qin2020_Article_High-dimensionalSign-constrain.pdf	Published version	3.66 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Qin, S
dc.contributor.author	Ding, H
dc.contributor.author	Wu, Y
dc.contributor.author	Liu, F https://orcid.org/0000-0002-5005-9129
dc.date.accessioned	2021-01-19T04:46:25Z
dc.date.available	2021-01-19T04:46:25Z
dc.date.issued	2020-01-01
dc.identifier.citation	Annals of the Institute of Statistical Mathematics, 2020, pp. 1-33
dc.identifier.issn	0020-3157
dc.identifier.issn	1572-9052
dc.identifier.uri	http://hdl.handle.net/10453/145490
dc.description.abstract	© 2020, The Institute of Statistical Mathematics, Tokyo. In this paper, we propose a non-negative feature selection/feature grouping (nnFSG) method for general sign-constrained high-dimensional regression problems that allows regression coefficients to be disjointly homogeneous, with sparsity as a special case. To solve the resulting non-convex optimization problem, we provide an algorithm that incorporates the difference of convex programming, augmented Lagrange and coordinate descent methods. Furthermore, we show that the aforementioned nnFSG method recovers the oracle estimate consistently, and that the mean-squared errors are bounded. Additionally, we examine the performance of our method using finite sample simulations and applying it to a real protein mass spectrum dataset.
dc.language	en
dc.publisher	Springer Science and Business Media LLC
dc.relation.ispartof	Annals of the Institute of Statistical Mathematics
dc.relation.isbasedon	10.1007/s10463-020-00766-z
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0104 Statistics
dc.subject.classification	Statistics & Probability
dc.title	High-dimensional sign-constrained feature selection and grouping
dc.type	Journal Article
utslib.for	0104 Statistics
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney
utslib.copyright.status	closed_access	*
dc.date.updated	2021-01-19T04:45:56Z
pubs.publication-status	Published

Abstract:

© 2020, The Institute of Statistical Mathematics, Tokyo. In this paper, we propose a non-negative feature selection/feature grouping (nnFSG) method for general sign-constrained high-dimensional regression problems that allows regression coefficients to be disjointly homogeneous, with sparsity as a special case. To solve the resulting non-convex optimization problem, we provide an algorithm that incorporates the difference of convex programming, augmented Lagrange and coordinate descent methods. Furthermore, we show that the aforementioned nnFSG method recovers the oracle estimate consistently, and that the mean-squared errors are bounded. Additionally, we examine the performance of our method using finite sample simulations and applying it to a real protein mass spectrum dataset.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/145490