Some single-precision routines have had to be ported from cblas. Later
on we could probably remove most of them since new scipy has
triangular_solve function and cholesky_delete could be implemented in
Python.
Small performance improvements (~10%) and it no longer uses custom dot
matrix function dot_over. Except for solve_triangular, all other
methods can operate on float32 arrays.
Thinkint out loud:
The complexity of LARS is the same as an OLS, and looking at the
benchmarks scikits/learn/glm/benchmarks/bench_glm.py it shows that
we are faster than scipy's lstsq, so I don't think there is much
more room for improvement. I'll benchmark against the R package
and see how far we are.
In arrayfuncs: removed dot_over and added min_pos.
Fabian Pedregosa