L1-norm loss based twin support vector machine for data recognition
L1-norm loss based twin support vector machine for data recognition
复制标题
DOI：
10.1016/j.ins.2016.01.023
复制
发表时间：
2016-05-01
影响因子：
8.1
通讯作者：
Chen, Dongjing
中科院分区：
文献类型：
--
作者：
Peng, Xinjun;Xu, Dong;Chen, Dongjing
提出了一种新的基于L-1范数损失的孪生支持向量机（L1 LTSVM）分类器。在这种L1 LTSVM中，每个优化问题同时最小化两类点的基于L-1范数的损失，这导致了与双支持向量机（TWSVM）不同的对偶问题。与TWSVM相比，该L1 LTSVM分类器的主要优点是：第一，L1 ILTSVM的对偶问题在学习过程中不需要求核矩阵的逆，这表明L1 LTSVM不仅具有部分稀疏的决策函数，而且可以通过SVM类学习算法有效地求解，从而适用于大规模问题。其次，该L1 LTSVM具有更完善和实用的几何解释。在几个合成数据集和基准数据集上的实验结果表明，L1 LTSVM在泛化性能上具有显著的优势。(C)2016 Elsevier Inc. All rights reserved.
This paper proposes a novel L-1-norm loss based twin support vector machine (L1LTSVM) classifier for binary recognition. In this L1LTSVM, each optimization problem simultaneously minimizes the L-1-norm based losses for the two classes of points, which results in a different dual problem compared with twin support vector machine (TWSVM). Compared with TWSVM, the main advantages of this L1LTSVM classifier are: first, the dual problems of L1ILTSVM do not need to inverse the kernel matrices during the learning process, indicating L1LTSVM not only has a partly sparse decision function, but also can be solved efficiently by some SVM-type learning algorithms, and then is suitable for large scale problems. Second, this L1LTSVM has more perfect and practical geometric interpretation. Experimental results on several synthetic as well as benchmark datasets indicate the significant advantage of L1LTSVM in the generalization performance. (C) 2016 Elsevier Inc. All rights reserved.