| 基于函数型数据的系数正则化回归的收敛速度 |
| |
| 引用本文： | 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,2015,35(2):281-286. |
| |
| 作者姓名： | 陶燕芳 唐轶 |
| |
| 作者单位： | 长江职业学院公共课部;云南民族大学数学与计算机学院 |
| |
| 基金项目： | Supported partially by National Natural Science Foundation of China(61105051) |
| |
| 摘 要： | 本文研究了基于函数型输入和1-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.
|
| 关 键 词： | 回归 函数型数据 1-正则化 Rademacher平均 |
| 收稿时间： | 2012/10/13 0:00:00 |
| 修稿时间： | 2014/1/21 0:00:00 |
ON THE CONVERGENCE RATE OF COEFFICIENT-BASED REGULARIZED REGRESSION FOR FUNCTIONAL DATA |
| |
| TAO Yan-fang and TANG Yi.ON THE CONVERGENCE RATE OF COEFFICIENT-BASED REGULARIZED REGRESSION FOR FUNCTIONAL DATA[J].Journal of Mathematics,2015,35(2):281-286. |
| |
| Authors: | TAO Yan-fang and TANG Yi |
| |
| Institution: | TAO Yan-fang;TANG Yi;Dept.of Basis,Changjiang Professional College;School of Math.and Computer Sci.,Yunnan University of Nationalities; |
| |
| Abstract: | 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. |
| |
| Keywords: | regression functional data l1-regularizer Rademacher average |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《数学杂志》浏览原始摘要信息 |
| 点击此处可从《数学杂志》下载免费的PDF全文 |
