On Tue, Mar 06, 2012 at 10:22:08PM +0100, Andreas wrote: > > I just tried my simple implementation, relying on scipy's BFGS, and it > > took approx. 1s to train on an artificial dataset with (n_samples=10000, > > n_features=20, n_classes=10), 15s on (n_samples=10000, n_features=100, > > n_classes=10). So I think, it can be ok for medium scale.
> Alex, Gael, what do you think about that? Don't know. Seems a bit slow to me, but that's a situation in which I badly want speed. What's the penalty (type and amount)? How does it compare to liblinear on a two-class problem? > Having some base implementation that can be improved with a better > optimizer later seems as a reasonable starting point. Well, before committing to anything, I would first want to know that it is the right algorithmic strategy, elsewhere I am afraid that we will have our design constrained. Gael ------------------------------------------------------------------------------ Keep Your Developer Skills Current with LearnDevNow! The most comprehensive online learning library for Microsoft developers is just $99.99! Visual Studio, SharePoint, SQL - plus HTML5, CSS3, MVC3, Metro Style Apps, more. Free future releases when you subscribe now! http://p.sf.net/sfu/learndevnow-d2d _______________________________________________ Scikit-learn-general mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
