[GPR] Support data normalization

[Yuki Koyama]

As the current implementation assumes the mean function to be zero constant, it is better to support data normalization, i.e., modify y so that mean(y) = 0.

Also, it is worth discussing the use of scaling, i.e., modify y so that var(y) = 1.

[Yuki Koyama]

This is called standardization (z-score normalization):
https://en.wikipedia.org/wiki/Feature_scaling
https://en.wikipedia.org/wiki/Standard_score