Best choices for regularization parameters in learning theory: On the bias-variance problem
Best choices for regularization parameters in learning theory: On the bias-variance problem
复制标题
DOI：
10.1007/s102080010030
复制
发表时间：
2002-11-01
影响因子：
3
通讯作者：
Smale, S
中科院分区：
文献类型：
--
作者：
Cucker, F;Smale, S
学习理论的目标（在其他一些情况下也是）是找到函数fρ：X→ Y的近似值，该函数只有通过一组对z=（xi，yi）m i= 1从X× Y上的未知概率测度ρ得出（fρ是ρ的“回归函数”）。
The goal of learning theory (and a goal in some other contexts as well) is to find an approximation of a function fρ: X→ Y known only through a set of pairs z=(xi, yi) m i= 1 drawn from an unknown probability measure ρ on X× Y (fρ is the “regression function” of ρ).