Generalization bounds of ERM algorithm with V-geometrically Ergodic Markov chains

Generalization bounds of ERM algorithm with V-geometrically Ergodic Markov chains
复制标题

V-几何遍历马尔可夫链 ERM 算法的泛化界限

DOI:
10.1007/s10444-011-9182-7
复制
发表时间:
2011-09
影响因子:
1.7
通讯作者:
Chang, Xiangyu
Chang, Xiangyu
中科院分区:
数学4区
文献类型:
--
作者:
Zou, Bin;Xu, Zongben;Chang, Xiangyu

文献摘要

参考文献

被引文献

相似文献

以往描述经验风险最小化(ERM)算法泛化能力的结果通常是基于独立同分布(I.I.D.)的假设。样本。在这篇文章中,我们建立了具有V-几何遍历马氏链样本的ERM算法一致收敛速度的第一指数界,作为一致收敛速度界的应用,我们还得到了具有V-几何遍历马氏链样本的ERM算法的广义界,并证明了具有V-几何遍历马氏链样本的ERM算法是相容的。本文的主要结果推广了I.I.D.的已知结果。对V几何遍历马氏链样本情形的观察。
The previous results describing the generalization ability of Empirical Risk Minimization (ERM) algorithm are usually based on the assumption of independent and identically distributed (i.i.d.) samples. In this paper we go far beyond this classical framework by establishing the first exponential bound on the rate of uniform convergence of the ERM algorithm with V-geometrically ergodic Markov chain samples, as the application of the bound on the rate of uniform convergence, we also obtain the generalization bounds of the ERM algorithm with V-geometrically ergodic Markov chain samples and prove that the ERM algorithm with V-geometrically ergodic Markov chain samples is consistent. The main results obtained in this paper extend the previously known results of i.i.d. observations to the case of V-geometrically ergodic Markov chain samples.
DOI: 10.1016/0047-259x(82)90083-5
发表时间: 1982-03
影响因子: 1.6
作者:
L. Devroye
通讯作者: L. Devroye
DOI: 10.1016/s0167-7152(98)00291-0
发表时间: 1999-08
影响因子: 0.8
作者:
P. Bartlett;G. Lugosi
通讯作者: P. Bartlett;G. Lugosi
DOI: 10.1007/978-1-4471-3267-7
发表时间: 1993
期刊: --
影响因子: --
作者:
S. Meyn;R. Tweedie
通讯作者: S. Meyn;R. Tweedie
DOI: 10.1214/aop/1176988847
发表时间: 1994
影响因子: 2.3
作者:
M. Talagrand
通讯作者: M. Talagrand
DOI: 10.1016/j.jspi.2007.09.003
发表时间: 2008-07
影响因子: 0.9
作者:
Xu, Yong-Li;Chen, Di-Rong
通讯作者: Chen, Di-Rong