【机器学习】MAP最大后验估计和ML最大似然估计区别

MAP：maximun a posteriori 最大后验估计

ML：maximun likelihood.

1 MAP

A maximum a posteriori probability (MAP) estimate is an estimate of an unknown quantity, that equals the mode of the posterior distribution. The MAP can be used to obtain a point estimate of an unobserved quantity on the basis of empirical data. It is closely related to the method of maximum likelihood (ML) estimation, but employs an augmented optimization objective which incorporates a prior distribution (that quantifies the additional information available through prior knowledge of a related event) over the quantity one wants to estimate. MAP estimation can therefore be seen as a regularization of ML estimation.

2 ML

3 区别

正则化等价于对模型参数引入先验分布，而L1正则化相当于参数中引入拉普拉斯分布先验，而L2分布则相当于引入了高斯分布先验。