Soft Upper-bound Minimal Complexity LP SVMs
Soft Upper-bound Minimal Complexity LP SVMs
复制标题
软上限最小复杂度 LP SVM
DOI：
10.1109/ijcnn52387.2021.9533540
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Shigeo Abe
中科院分区：
文献类型：
--
作者：
Shigeo Abe
最小复杂度线性规划支持向量机(MLP SVM)是为了解决最小复杂度机(MCM)的无界非唯一解问题而提出的。 MLP SVM 最小化最大边际（即训练数据和分离超平面之间的最大距离）并最大化最小边际。因此，如果包含异常值并且它们影响分离超平面的斜率和位置，则泛化能力可能会变差。为了解决这个问题，在本文中，我们提出了软上限MLP SVM（SLP SVM），其中通过引入松弛变量来抑制影响超平面的异常值。这个引入导致了超参数的增加。我们讨论如何减少超参数的数量以加快模型选择。通过计算机实验，我们使用二类和多类问题比较了 SLP SVM 与 MLP SVM、MCM 和其他基于 SVM 的分类器的泛化能力和训练时间。
The minimal complexity linear programming support vector machine (MLP SVM) was proposed to solve the problem of unbounded non-unique solutions of the minimal complexity machine (MCM). The MLP SVM minimizes the maximum margin that is the maximum distance between training data and the separating hyperplane as well as maximizes the minimum margin. Therefore, the generalization ability may be worsened if outliers are included and they affect the slope and the location of the separating hyperplane. To solve this problem, in this paper, we propose the soft upper-bound MLP SVM (SLP SVM), in which the outliers that affect the hyperplane are suppressed by introducing the slack variables. This introduction leads to the increase of hyperparameters. We discuss how to reduce the number of hyperparameters to speed up model selection. By computer experiments we compare the generalization ability and training time of the SLP SVM with those of the MLP SVM, MCM, and other SVM based classifiers using two-class and multiclass problems.