Sparse Distance Weighted Discrimination

Boxiang Wang; Hui Zou

doi:10.1080/10618600.2015.1049700

Back

Journal article

Peer reviewed

Sparse Distance Weighted Discrimination

Boxiang Wang and Hui Zou

Journal of Computational and Graphical Statistics, Vol.25(3), pp.826-838

07/02/2016

DOI: 10.1080/10618600.2015.1049700

View Online

Abstract

Distance weighted discrimination (DWD) was originally proposed to handle the data piling issue in the support vector machine. In this article, we consider the sparse penalized DWD for high-dimensional classification. The state-of-the-art algorithm for solving the standard DWD is based on second-order cone programming, however such an algorithm does not work well for the sparse penalized DWD with high-dimensional data. To overcome the challenging computation difficulty, we develop a very efficient algorithm to compute the solution path of the sparse DWD at a given fine grid of regularization parameters. We implement the algorithm in a publicly available R package sdwd. We conduct extensive numerical experiments to demonstrate the computational efficiency and classification performance of our method.

DWD

High-dimensional classification

SVM

Details

Title: Subtitle: Sparse Distance Weighted Discrimination
Creators: Boxiang Wang
Hui Zou
Resource Type: Journal article
Publication Details: Journal of Computational and Graphical Statistics, Vol.25(3), pp.826-838
DOI: 10.1080/10618600.2015.1049700
ISSN: 1061-8600
eISSN: 1537-2715
Publisher: Taylor & Francis
Language: English
Date published: 07/02/2016
Academic Unit: Statistics and Actuarial Science
Record Identifier: 9983985701202771

Metrics

17 Record Views

20 Times Cited - Web of Science