R package notes

[bwlewis]

We'll roll all these methods in to an R package.

But, the SVD Newton method will be the primary non-distributed method. We should add the following to it:

1. R-like subset selection
2. Full set of output stats

Also note that the termination criterion is not the same as R, we should change that.

[RoyiAvital]

I'd add to the documentation at http://bwlewis.github.io/GLM/ more intuition about how does applying the G function helps.
Namely if I do linear regression what would be the difference between minimizing the regular cost function to the logistic cost function.