数学杂志Issue(2)：281-286,6.
基于函数型数据的系数正则化回归的收敛速度
ON THE CONVERGENCE RATE OF COEFFICIENT-BASED REGULARIZED REGRESSION FOR FUNCTIONAL DATA
摘要
Abstract
This paper investigates the generalization performance of least square regression with functional data and‘1-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.关键词
回归/函数型数据/`1 -正则化/Rademacher平均Key words
regression/functional data/‘1-regularizer/Rademacher average分类
数理科学引用本文复制引用
陶燕芳,唐轶..基于函数型数据的系数正则化回归的收敛速度[J].数学杂志,2015,(2):281-286,6.基金项目
Supported partially by National Natural Science Foundation of China (61105051) （61105051）
