文献类型：期刊文献

英文题名：Error Analysis on Hermite Learning with Gradient Data

作者：Sheng, Baohuai[1];Wang, Jianli[1];Xiang, Daohong[2]

机构：[1]Shaoxing Univ, Dept Math, Shaoxing 312000, Zhejiang, Peoples R China;[2]Zhejiang Normal Univ, Dept Math, Jinhua 321004, Zhejiang, Peoples R China

年份：2018

卷号：39

期号：4

起止页码：705

外文期刊名：CHINESE ANNALS OF MATHEMATICS SERIES B

收录：SCI-EXPANDED(收录号：WOS:000448793100008)、、WOS

基金：This work was supported by the National Natural Science Foundation of China (No. 11471292).

语种：英文

外文关键词：Hermite learning; Gradient learning; Learning rate; Convex analysis; Multitask learning; Differentiable reproducing kernel Hilbert space

外文摘要：This paper deals with Hermite 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.