Inherit from logistic regression in sklearn

[yngvem]

Currently, the two-class logistic regression model and multi-class logistic regression model is implemented differently. This is because I was able to find a better bound for the Lipschitz coefficient with the two-class problem. However, this artificial difference is not very intuitive, especially considering that it is regarded the same in sklearn.

A good improvement would be to simply inherit from Logistic regression in sklearn and overload the necessary functions.