|
|
| |
| Error Analysis on H\'{e}rmite Learning with Gradient Data |
| |
Citation： |
Baohuai SHENG,Jianli WANG,Daohong XIANG.Error Analysis on H\'{e}rmite Learning with Gradient Data[J].Chinese Annals of Mathematics B,2018,39(4):705~720 |
| Page view： 731
Net amount： 627 |
Authors： |
Baohuai SHENG; Jianli WANG;Daohong XIANG |
Foundation： |
This work was supported by the National Natural Science
Foundation of China (No.11471292). |
|
|
| Abstract： |
This paper deals with H\'{e}rmite 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 |
Classification： |
41A25, 46E22, 68Q32, 68T05, 90C25 |
|
|
Download PDF Full-Text
|
