一种基于模拟退火的支持向量机超参数优化算法

An Optimizing Algorithm of Super-parameters for SVM Based on Simulation Annealing

基于统计学习理论的支持向量机技术以探求小样本情况下如何获得更好的机器学习规律而见长,与基于经验风险最小化原则的机器学习方法相比能够获得更佳的泛化能力,相关超参数的选择对其分类或回归性能有较大影响。针对径向基核支持向量机超参数优化问题,提出了一种改进的基于模拟退火算法的高效多目标优化算法,并详细讨论了优化寻优过程中搜索空间、初始可行解、初温和最优目标函数的设计方法。通过在多个标准数据集上的测试验证,证实了本文所提算法的可行性和有效性。

Based on the statistical learning theory support vector machine focuses on the machine learning strategies under small samples and gets better generalization ability than that of those tools based on the experience risk minimization principle. Its classing or regression performance will be affected by relative superparameters. An improved multi-object optimization algorithm based on simulated annealing is proposed and applied to super-parameters optimization of the support vector machine with a RBF kernel. Then selection of proper searching space, initial feasible solution, initial temperature and design of an optimal object function are discussed in detail. The validation on the some standard data sets is carried out and its feasibility and effectiveness are confirmed.