Knowledge Commons of Institute of Automation,CAS
Robust support vector machines based on the rescaled hinge loss function | |
Xu, Guibiao1![]() ![]() | |
发表期刊 | PATTERN RECOGNITION
![]() |
2017-03-01 | |
卷号 | 63页码:139-148 |
文章类型 | Article |
摘要 | The support vector machine (SVM) is a popular classifier in machine learning, but it is not robust to outliers. In this paper, based on the Correntropy induced loss function, we propose the resealed hinge loss function which is a monotonic, bounded and nonconvex loss that is robust to outliers. We further show that the hinge loss is a special case of the proposed resealed hinge loss. Then, we develop a new robust SVM based on the resealed hinge loss. After using the half-quadratic optimization method, we find that the new robust SVM is equivalent to an iterative weighted SVM, which can help explain the robustness of iterative weighted SVM from a loss function perspective. Experimental results confirm that the new robust SVM not only performs better than SVM and the existing robust SVMs on the datasets that have outliers, but also presents better sparseness than SVM. |
关键词 | Support Vector Machine Robustness Rescaled Hinge Loss Half-quadratic Optimization |
WOS标题词 | Science & Technology ; Technology |
DOI | 10.1016/j.patcog.2016.09.045 |
关键词[WOS] | CLASSIFICATION ; MINIMIZATION ; RECOGNITION ; CORRENTROPY ; SIGNAL |
收录类别 | SCI |
语种 | 英语 |
项目资助者 | NSFC(61273196) ; China Scholarship Council |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000389785900011 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/13367 |
专题 | 多模态人工智能系统全国重点实验室_多媒体计算 |
作者单位 | 1.Chinese Acad Sci, Inst Automat, NLPR, Beijing 100190, Peoples R China 2.Univ Florida, CNEL, Dept Elect & Comp Engn, Gainesville, FL 32611 USA |
第一作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Xu, Guibiao,Cao, Zheng,Hu, Bao-Gang,et al. Robust support vector machines based on the rescaled hinge loss function[J]. PATTERN RECOGNITION,2017,63:139-148. |
APA | Xu, Guibiao,Cao, Zheng,Hu, Bao-Gang,&Principe, Jose C..(2017).Robust support vector machines based on the rescaled hinge loss function.PATTERN RECOGNITION,63,139-148. |
MLA | Xu, Guibiao,et al."Robust support vector machines based on the rescaled hinge loss function".PATTERN RECOGNITION 63(2017):139-148. |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论