期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

基于积分算子技巧的容量相关估计

Integral operator based capacity dependent estimation
下载PDF
导出
摘要 利用与积分算子特征值下降速率有关的两种容量相关条件,在抽样是同分布且样本是独立选取的情况下,通过积分算子技巧和假设概率随机事件的方法给出了正则化最小二乘回归学习算法的一致性误差界,并将正则化最小二乘回归学习算法的学习速率提高到了O(m-β(1+2β))。 We derive the consistency error bounds and improve the learning rate to O（ m-β（1 ＋2β ） by integral operator and assumption of probability random event, two capacity conditions dependent on the decay rates of the characteristic value of the integral operator and the assumption of independent and identical distribution.
作者 郭芹 蔡斌雷
机构地区 济南大学泉城学院基础部 山东省科学院情报研究所
出处 《山东科学》 CAS 2013年第4期7-10,15,共5页 Shandong Science
基金 国家自然科学基金(11071276)
关键词 积分算子 最小二乘回归 误差界 学习速率 integral operator least squares regression error bound learning rate
分类号 O241.3 [理学—计算数学]
  • 相关文献

参考文献11

  • 1SMALE S, ZHOU D X. Learning theory estimates via integral operators and their approximations [ J ]. Constructive Approximation, 2007, 26(2) : 153 -172.
  • 2SUN H W, WU Q. A note on application of integral operator in learning theory [ J ]. Applied and Computational Harmonic Analysis, 2009, 26(3) : 416 -421.
  • 3SUN H W, WU Q. Regularized least square regression with dependent Samples [ J ]. Advances in Computational Mathematics, 2010, 32(2) :175 - 189.
  • 4郭芹,孙红卫.基于弱相关抽样的系数正则化的一致性分析[J].济南大学学报（自然科学版）,2010,24(1):99-103. 被引量：3
  • 5WU Q, YING Y M, ZHOU D X. Learning rates of least-square regularized regression [ J ]. Foundation of Computational Mathematics, 2006, 6(2) : 171 - 192.
  • 6XU Y L, CHEN D R. Learning rates of regularized regression for exponentially strongly mixing sequence [ J]. Journal of Statistic Planning and Inference, 2008, 138(7) : 2180 -2189.
  • 7BOUSQUET O, ELISSEEFF A. Stability and generalization [ J ]. Journal of Machine Learning Research, 2002, 2 (3) : 499 -526.
  • 8ZHANG T. Leave-one-out bounds for kernel methods [J]. Neural Computation, 2003, 15(6) : 1397 - 1437.
  • 9ARONSZAJN N. Theory of reproducing kernels [ J ]. Trans. Amer Math Soc, 1950, 68 ( 1 ) : 337 - 404.
  • 10GUO Q, SUN H W. Improved asymptotic analysis of least square regression learning[ J]. Journal of Computational Information Systems, 2011,7(6) : 2149 -2157.

二级参考文献11

  • 1CUCKER F, SMALE S. On the mathematical foun-dations of learning [J].Bull Amer Soc,2001,39 : 1 - 49.
  • 2WU Qiang,YING Yiming, ZHOU Dingxuan. Learning rates of least square regularized regression [ J ]. Found Comput Math, 2006,6 : 171 - 192.
  • 3SMALE S, ZHOU Dingxuan. Learning theory estimates via integral operators and their approximations [ J ]. Constr Approx, 2007,26 : 153 - 172.
  • 4WU Qiang,ZHOU Dingxuan. Learning with sample dependent hypothesis spaces[J].Comput Math Appl, 2008,56 (11 ) :2896 - 2907.
  • 5ARONSZAJN N. Theory of reproducing kernels [ J ]. Trans Amer Math Soc, 1950,8:337 -404.
  • 6MODHA D S. Minimum complexity regression estimation with weakly dependent observations[J].IEEE Trans Inform Theory,1996,42:2133 -2145.
  • 7SUN Hongwei,WU Qiang. Application of integral operator for regularized leastsquare regression [J]. Mathematical and Computer Modelling,2009, 49 ( 1 ) :276 - 285.
  • 8SUN Hongwei,WU Qiang. A note on application of integral operator in learning theory [ J ]. Applied and Computational Harmonic Analysis,2009,26 : 416 -421.
  • 9HIRSCH F,ACOMBE G. Elements of Functional Analysis[M]. New York : pringer Verlag, 1999,52 - 64.
  • 10DEHLING H, PHILIPP W. Almost sure invariance principles for weakly dependent vectorvalued random variables[ J]. Ann Probability, 1982,10:689 - 701.

共引文献2

山东科学
2013年 第4期

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