期刊文献+

RKHS中正则化学习算法的推广误差界

Generalization error bound for regularization-based learning algorithm in RKHS
下载PDF
导出
摘要 研究了再生核希尔伯特空间(RKHS)中的正则化学习算法,证明了其推广误差可分解为两个部分:逼近误差和估计误差,并应用VC维和算法稳定性给出了相应界,最后联立这两个结果证明了正则化学习算法具有好的推广性. Regularization-based learning algorithm in Reproducting Kernel Hilbert Space (RKHS) is studied.Its generalization error is proved to be decomposed into two parts:an approximation one and an estimation one. They are bounded respectively by VC dimension and algorithmic stability property. Finally,according to these two results,it can be proved that regularization-based learning algorithm has good generalization ability.
出处 《湖北大学学报(自然科学版)》 CAS 北大核心 2005年第1期15-18,共4页 Journal of Hubei University:Natural Science
基金 国家自然科学基金(10371033)资助课题
关键词 误差界 再生核 希尔伯特空间 正则化 证明 逼近误差 推广 学习算法 VC维 算法稳定性 generalization error regularization algorithmic stability VC-bound
  • 相关文献

参考文献6

  • 1Niyogi P,Girosi F. Generalization bounds for function approximation from scattered noisy data[J].Advances in Computional Mathematics,1999,10:51~80.
  • 2Cuker F,Smale S.On the mathematical foundations in learning[J].Bulletin of the American Society (New Series),2002,39(1):1~49.
  • 3Evgeniou T,Pontil M,Poggio T.Regularization networks and support vector machines[J].Advances in Computational Mathematics,2002,13:1~50.
  • 4Vapnik V.Statistical learning theory[M].New York:John Wiley,1998.
  • 5Bousquet O,Elisseeff A.Stability and generalization[J].Journal of Machine Learning Research,2002,2:499~526.
  • 6Kutin S,Niyogi P.Almost-everywhere algorithmic stability and generalization error[A].Proceedings of the 18th Annual Conferece on UAI[C].San Francisco:Morgan Kaufmann Publishers,2002.275~282.

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部