一种大规模支持向量机的高效求解算法  

Efficient Algorithm for Large-scale Support Vector Machine

作　　者：冯昌[1] 李子达 廖士中[1] 

机构地区：[1]天津大学计算机科学与技术学院,天津300072

出　　处：《计算机科学》2015年第9期195-198,共4页Computer Science

基　　金：国家自然科学基金(61170019)资助

摘　　要：现有大规模支持向量机求解算法需要大量的内存资源和训练时间,通常在大集群并行环境下才能实现。提出了一种大规模支持向量机(SVM)的高效求解算法,以在个人PC机求解大规模SVM。它包括3个步骤:首先对大规模样本进行子采样来降低数据规模;然后应用随机傅里叶映射显式地构造随机特征空间,使得可在该随机特征空间中应用线性SVM来一致逼近高斯核SVM;最后给出线性SVM在多核环境下的并行实现方法以进一步提高求解效率。标准数据集的对比实验验证了该求解算法的可行性与高效性。The algorithm for solving large-scale support vector machine （SVM） needs large memory requirement and computation time. Therefore, large-scale SVMs are performed on computer clusters or supercomputers. An efficient al- gorithm for large-scale SVM was presented, which can be operated on a daily-life PC. First, the large-scale training examples were subsampled to reduce the data size. Then, the random Fourier mapping was explicitly applied to the sub- sample to generate the random feature space,making it possible to apply a linear SVM to uniformly approximate to the Gaussian kernel SVM. Finally, a parallelized linear SVM algorithm was implemented to speed up the training further. Experimental results on benchmark datasets demonstrate the feasibility and efficiency of the proposed algorithm.

关 键 词：大规模支持向量机 子采样 随机傅里叶特征 并行线性支持向量机 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]