More comments on C p

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Hyperparameter optimization with approximate gradient (2016, background): “ion can be a goodness of ﬁt on unseen data, such as a cross-validation loss, or some criteria of model quality on the train set such as SURE (Stein, 1981), AIC/BIC (Liu and Yang, 2011) or Mallows C p(Mallows, 1973), to name a few. Choosing the appropriate set of hyperparameters has often a dramatic ”
Degrees of freedom in lasso problems (2011, background): “(one for each predictor variable). Furthermore, we can decompose the risk of the linear t ^yas Ek^y k2 2 = Eky^ yk n˙2 + 2p˙2; a well-known identity that leads to the derivation of the C pstatistic (Mallows 1973). For a general tting procedure g, the motivation for the denition (4) comes from the an”