Regularization is common in machine learning but not in statistics. Another advantage of regularization is that it improves numerical stability.机器学习中正则化是非常普遍的在使用,但在统计学,数据科学中用的不多,它可以提高模型的数值稳定性。
看过的最好的讲训练集验证集测试集的文章!
如何正确使用机器学习中的训练集、验证集和测试集?
这个图完美了
不正则化的线性回归经过:
L1正则化-------LASSO回归 least absolute shrinkage and selection operator
L2正则化-------ridge回归
L1+L2 正则化 elastic net 回归
elastic net is a linear regression model trained with both and -norm regularization of the coefficients.
Elastic-net is useful when there are multiple features which are correlated with one another. Lasso is likely to pick one of these at random, while elastic-net is likely to pick both.
A practical advantage of trading-off between Lasso and Ridge is that it allows Elastic-Net to inherit some of Ridge’s stability under rotation.
线性回归:
岭回归:
lasso回归:
elastic net回归:
正则化项是L1和L2的凸组合,Convex combination of L2 and L1