%0 Journal Article
%T 基于函数型数据的系数正则化回归的收敛速度<br>ON THE CONVERGENCE RATE OF COEFFICIENT-BASED REGULARIZED REGRESSION FOR FUNCTIONAL DATA
%A 作者
%A 陶燕芳
%A 唐轶
%J 数学杂志
%D 2015
%X 本文研究了基于函数型输入和l1-正则化的最小二乘回归问题的推广性能.利用基于Rademacher平均的分析技术,获得了学习速度的估计,推广了已有的欧式空间有限维输入结果.<br>This paper investigates the generalization performance of least square regression with functional data and l1-regularizer. The estimate of learning rate is established by Rademacher average technique. The theoretical result is a natural extension for coefficient-based regularized regression when input space is a subset of infinite-dimensional Euclidean space
%K 回归 函数型数据 l1-正则化 Rademacher平均&lt
%K br&gt
%K regression functional data l1-regularizer Rademacher average
%U http://sxzz.whu.edu.cn/sxzz/ch/reader/view_abstract.aspx?file_no=20150207&flag=1