A New Support Vector Machine Plus with Pinball Loss

Wenxin Zhu, Yunyan Song and Yingyuan Xiao ()
Additional contact information
Wenxin Zhu: TianJin Agricultural University
Yunyan Song: Tianjin University of Technology
Yingyuan Xiao: Tianjin University of Technology

Journal of Classification, 2018, vol. 35, issue 1, No 4, 52-70

Abstract: Abstract The hinge loss support vector machine (SVM) is sensitive to outliers. This paper proposes a new support vector machine with a pinball loss function (PSVM+). The new model is less sensitive to noise, especially the feature noise around the decision boundary. Furthermore, the PSVM+ is more stable than the hinge loss support vector machine plus (SVM+) for re-sampling. It also embeds the additional information into the corresponding optimization problem, which is helpful to further improve the learning performance. Meanwhile, the computational complexity of the PSVM+ is similar to that of the SVM+.

Keywords: Support vector machine; SVM+; Additional information; Re-sampling; Pinball loss (search for similar items in EconPapers)
Date: 2018
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://link.springer.com/10.1007/s00357-018-9249-y Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:jclass:v:35:y:2018:i:1:d:10.1007_s00357-018-9249-y

Ordering information: This journal article can be ordered from
http://www.springer. ... hods/journal/357/PS2

DOI: 10.1007/s00357-018-9249-y

Access Statistics for this article

Journal of Classification is currently edited by Douglas Steinley

More articles in Journal of Classification from Springer, The Classification Society
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().