Asymmetric nu-twin support vector regression
Asymmetric nu-twin support vector regression
复制标题
非对称nu-twin支持向量回归
DOI：
10.1007/s00521-017-2966-z
复制
发表时间：
2018
影响因子：
6
通讯作者：
Yang Zhiji
中科院分区：
文献类型：
--
作者：
Xu Yitian;Li Xiaoyan;Pan Xianli;Yang Zhiji
双支持向量回归（Twin Support Vector Regression，TSVR）的目标是通过求解一对较小的二次规划问题（Quadratic Programming Problems，QPP）来寻找训练点的对S不敏感的上下界函数，而不是像传统的SVR那样求解一个大的问题。𝜖因此理论上TSVR比SVR工作得更快。然而，TSVR对上界以上和下界以下的点给予同等重视，这导致对回归函数的影响相同。事实上，不同位置的点对回归量有不同的影响。受此启发，提出了一种基于弹球损失函数的非对称ν-孪生支持向量回归机（Asy-ν-TSVR）.该算法通过调整参数ν和p，可以有效地控制拟合误差。因此，它提高了泛化能力。此外，我们研究了样本的分布，并给出了样本位于不同位置的上界。在一个人工数据集、11个基准数据集和一个真实的小麦数据集上的数值实验证明了该算法的有效性。
Twin support vector regression (TSVR) aims at finding𝜖-insensitive up- and down-bound functions for the training points by solving a pair of smaller-sized quadratic programming problems (QPPs) rather than a single large one as in the conventional SVR. So TSVR works faster than SVR in theory. However, TSVR gives equal emphasis to the points above the up-bound and below the down-bound, which leads to the same influences on the regression function. In fact, points in different positions have different effects on the regressor. Inspired by it, we propose an asymmetricν-twin support vector regression based on pinball loss function (Asy-ν-TSVR). The new algorithm can effectively control the fitting error by tuning the parametersνandp. Therefore, it enhances the generalization ability. Moreover, we study the distribution of samples and give the upper bounds for the samples locating in different positions. Numerical experiments on one artificial dataset, eleven benchmark datasets and a real wheat dataset demonstrate the validity of our proposed algorithm.