An incremental learning algorithm for Lagrangian support vector machines
An incremental learning algorithm for Lagrangian support vector machines
复制标题
拉格朗日支持向量机的增量学习算法
DOI：
10.1016/j.patrec.2009.07.006
复制
发表时间：
2009-11
影响因子：
5.1
通讯作者：
Shao, Xiaojian
中科院分区：
文献类型：
--
作者：
He, Guoping;Hou, Weizhen;Zeng, Qingtian;Duan, Hua;Shao, Xiaojian
近年来，增量学习在理论和应用上都受到了越来越多的关注。提出了拉格朗日支持向量机（LSVM）的增量学习算法。LSVM是对标准线性支持向量机分类算法的改进，它可以使无约束可微凸规划问题最小化。通过一个简单的线性收敛的迭代格式得到了这个规划的解。求解算法中的矩阵求逆在算法开始时被转换为原始输入空间的维数加1的阶数。该算法使用了Sherman-Morrison-伍德伯里恒等式来减少计算时间。本文提出的LSVM增量学习算法包括在线增量学习和批量增量学习两种情况。由于增量后矩阵的求逆是基于先前计算的信息来求解的，因此不需要重复计算过程。实验结果表明，该算法具有上级的优越性。
Incremental learning has attracted more and more attention recently, both in theory and application. In this paper, the incremental learning algorithms for Lagrangian support vector machine (LSVM) are proposed. LSVM is an improvement to the standard linear SVM for classifications, which leads to the minimization of an unconstrained differentiable convex programming. The solution to this programming is obtained by an iteration scheme with a simple linear convergence. The inversion of the matrix in the solving algorithm is converted to the order of the original input space’s dimensionality plus one at the beginning of the algorithm. The algorithm uses the Sherman–Morrison–Woodbury identity to reduce the computation time. The incremental learning algorithms for LSVM presented in this paper include two cases that are namely online and batch incremental learning. Because the inversion of the matrix after increment is solved based on the previous computed information, it is unnecessary to repeat the computing process. Experimental results show that the algorithms are superior to others.
登录
查看更多内容
影响因子：
7.5
作者：
J. C. Schlimmer;R. Granger
通讯作者：
J. C. Schlimmer;R. Granger
DOI：
10.1137/s1052623400374379
发表时间：
2002-08
期刊：
SIAM J. Optim.
影响因子：
--
作者：
M. Ferris;T. Munson
通讯作者：
M. Ferris;T. Munson
影响因子：
7.5
作者：
J. C. Schlimmer;R. Granger
通讯作者：
J. C. Schlimmer;R. Granger
影响因子：
2.5
作者：
R. Lordo
通讯作者：
R. Lordo
影响因子：
--
作者：
Mangasarian, OL;Musicant, DR
通讯作者：
Musicant, DR