A note on application of integral operator in learning theory
A note on application of integral operator in learning theory
复制标题
DOI：
10.1016/j.acha.2008.10.002
复制
发表时间：
2009-05
影响因子：
2.5
通讯作者：
Hongwei Sun;Qiang Wu
中科院分区：
文献类型：
--
作者：
Hongwei Sun;Qiang Wu
利用正算子的平方根的性质，改进了可复制核Hilbert空间中正则化最小二乘回归的一致性分析。当采样序列满足强混合条件时，得到更清晰的误差界和更快的学习率。
By the aid of the properties of the square root of positive operators we refine the consistency analysis of regularized least square regression in a reproducing kernel Hilbert space. Sharper error bounds and faster learning rates are obtained when the sampling sequence satisfies a strongly mixing condition.