| Error Analysis on Hérmite Learning with Gradient Data |
| |
| 作者姓名： | Baohuai SHENG Jianli WANG Daohong XIANG |
| |
| 摘 要： | This paper deals with Hérmite learning which aims at obtaining the target function from the samples of function values and the gradient values. Error analysis is conducted for these algorithms by means of approaches from convex analysis in the framework of multi-task vector learning and the improved learning rates are derived.
|
| 收稿时间： | 2015/2/9 0:00:00 |
| 修稿时间： | 2016/5/28 0:00:00 |
Error Analysis on H\'{e}rmite Learning with Gradient Data |
| |
| Baohuai SHENG,Jianli WANG,Daohong XIANG.Error Analysis on H\''{e}rmite Learning with Gradient Data[J].Chinese Annals of Mathematics,Series B,2018,39(4):705-720. |
| |
| Authors: | Baohuai SHENG Jianli WANG and Daohong XIANG |
| |
| Institution: | 1.Department of Mathematics,Shaoxing Univeristy,Shaoxing,China;2.Department of Mathematics,Zhejiang Normal University,Jinhua,China |
| |
| Abstract: | This paper deals with Hérmite learning which aims at obtaining the target function from the samples of function values and the gradient values. Error analysis is conducted for these algorithms by means of approaches from convex analysis in the framework of multi-task vector learning and the improved learning rates are derived. |
| |
| Keywords: | H''{e}rmite learning Gradient learning Learning rate Convexanalysis Multitask learning Differentiable reproducing kernelHilbert space |
| 本文献已被 CNKI SpringerLink 等数据库收录！ |
| 点击此处可从《数学年刊B辑(英文版)》浏览原始摘要信息 |
| 点击此处可从《数学年刊B辑(英文版)》下载免费的PDF全文 |
