A Novel Sequential Minimal Optimization Algorithm for Support Vector Regression
A Novel Sequential Minimal Optimization Algorithm for Support Vector Regression
复制标题
DOI：
10.1007/11893028_92
复制
发表时间：
2006-10
期刊：
影响因子：
--
通讯作者：
Jun Guo;Norikazu Takahashi;T. Nishi
中科院分区：
文献类型：
--
作者：
Jun Guo;Norikazu Takahashi;T. Nishi
提出了一种新的支持向量回归机序列最小优化算法。该算法是基于Flake和Lawrence的SMO算法，其中求解的是l个变量的凸优化问题，而不是标准的2l个变量的二次规划问题，其中l是训练样本的个数，但工作集的选择策略有很大的不同。实验结果表明，该算法比Flake和Lawrence的SMO算法速度快得多，与最快的传统SMO算法相当。
A novel sequential minimal optimization (SMO) algorithm for support vector regression is proposed. This algorithm is based on Flake and Lawrence’s SMO in which convex optimization problems withlvariables are solved instead of standard quadratic programming problems with 2lvariables wherelis the number of training samples, but the strategy for working set selection is quite different. Experimental results show that the proposed algorithm is much faster than Flake and Lawrence’s SMO and comparable to the fastest conventional SMO.