| 基于out-of-bag样本的随机森林算法的超参数估计 |
| |
| 引用本文： | 李毓,张春霞.基于out-of-bag样本的随机森林算法的超参数估计[J].系统工程学报,2011,26(4). |
| |
| 作者姓名： | 李毓 张春霞 |
| |
| 作者单位： | 1. 信阳师范学院经济与管理学院,河南信阳,464000
2. 西安交通大学理学院统计金融系,陕西西安,710049 |
| |
| 基金项目： | 教育部人文与社会科学基金资助项目(09YJA790174); 教育部博士学科点专项科研基金(20100201120048); 河南省软科学基金资助项目(102400450126) |
| |
| 摘 要： | 随机森林是一种有效的分类树集成算法,但为了使它具有较高的预测精度,要采用某种方法确定其超参数的最优值.在不额外增加计算复杂性的前提下,提出了一种基于out-of-bag样本估计其超参数取值的方法.仿真试验的结果表明,利用文中提出的方法所选取的超参数在多数情况下都能使随机森林算法的分类效果达到最优.
|
| 关 键 词： | 集成学习 随机森林 泛化能力 Bootstrap样本 out-of-bag样本 交叉确认法 |
Estimation of the hyper-parameter in random forest based on out-of-bag sample |
| |
| LI Yu,ZHANG Chun-xia.Estimation of the hyper-parameter in random forest based on out-of-bag sample[J].Journal of Systems Engineering,2011,26(4). |
| |
| Authors: | LI Yu ZHANG Chun-xia |
| |
| Institution: | LI Yu~1,ZHANG Chun-xia~2 (1.School of Economics and Management,Xinyang Normal University,Xinyang 464000,China,2.Department of Statistics and Finance,Faculty of Science,Xi'an Jiaotong University,Xi'an 710049,China) |
| |
| Abstract: | Random forest(RF) is an effective decision tree ensemble method.In order to achieve its best performance,however,the optimal value of the hyper-parameter in RF needs to be estimated by an appropriate method.Under the condition that the computational cost is not additionally consumed,this paper proposes a new approach to estimate the hyper-parameter based on the out-of-bag sample.The experiments conducted by some UCI real-world data sets show that RF with the hyper-parameter estimated by the proposed method ... |
| |
| Keywords: | ensemble learning random forest generalization capability bootstrap sample out-of-bag sample cross-validation method |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
