基于Rademacher复杂度的ν-SVM的推广误差

The Generalization Error Based on Rademacher Complexity of ν-SVM

下载PDF

导出

摘要运用Rademacher复杂度得到了ν-SVM的推广误差和风险的上界. We get both the generalization error and the upper bound of ν-SVM by using the Rademacher complexity.

作者陈湘

机构地区咸宁学院数学与统计学院

出处《咸宁学院学报》 2008年第6期16-18,共3页 Journal of Xianning University

关键词 ν-SVM Rademacher复杂度推广误差 ν-SVM Rademacher complexity Generalization error

参考文献7

1V. Koltehinskii and D. Panchenko. Empirical margin distributions and bounding the generalization error of combined classifiers[J]. The Annals of Statistics, 2002, 30(1) :1 - 50. 被引量：1
2Michael J. Kearns, Yishay Mansour, Andrew Y. Ng, Dana Ron. An experimental and theoretical comparison of model selection methods[J]. Machine Learning, 1997, 27:7 - 50. 被引量：1
3V. Koltchinskii. Rademacher panalties and structural risk minimization[ J]. IEEE Transactions on Information Theory, 2001,47(5) :1 902 - 1 914. 被引量：1
4S. Mendelson. A few notes on statistical learning theory in Advanced Lectures in Machine Learning[C].LNCS 2600, Springer, 2003.1 - 40. 被引量：1
5Boucheron, S. , O. Bousquet and G. Lugosi: Theory of Classification:A Survey of Some Recent Advances[J]. ESAIM: Probability and Statistics, 2005, 9:323- 375. 被引量：1
6Peter L. Bartlett and S. Mendelson. Rademaeher and Gaussian complexities :risk bounds and structural results[J]. Journal of Machine Learning Research, 2002, 3:463 - 482. 被引量：1
7Peter L. Bartlett, S. Boucheron and G. Lugosi. Model selection and error estlmation[J]. Machine Learning, 2001,48:85 - 113. 被引量：1

咸宁学院学报

2008年第6期

内容加载中请稍等...