Regularization paths of L-1-penalized ROC Curve-Optimizing Support Vector Machines
- Authors
- Kim, Hyungwoo; Sohn, Insuk; Shin, Seung Jun
- Issue Date
- Dec-2021
- Publisher
- WILEY
- Keywords
- imbalanced binary classification; piecewise linear paths; receiver operator characteristic curve; support vector machine
- Citation
- STAT, v.10, no.1
- Indexed
- SCIE
SCOPUS
- Journal Title
- STAT
- Volume
- 10
- Number
- 1
- URI
- https://scholar.korea.ac.kr/handle/2021.sw.korea/135564
- DOI
- 10.1002/sta4.400
- ISSN
- 2049-1573
- Abstract
- The receiver operator characteristic (ROC) curve is one of the most popular tools to evaluate the performance of binary classifiers in a variety of applications. Rakotomamonjy (2004) proposed the ROC-SVM that directly optimizes the area under the ROC curve instead of the prediction accuracy. In this article, we study the L-1-penalized ROC-SVM that directly optimizes the ROC curve. We first show that the L-1-penalized ROC-SVM has piecewise linear regularization paths and then develop an efficient algorithm to compute the entire paths, which greatly facilitates its tuning procedure.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Political Science & Economics > Department of Statistics > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholar.korea.ac.kr/handle/2021.sw.korea/135564)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.