On Sat, Feb 4, 2012 at 1:16 AM, Vlad Niculae <[email protected]> wrote:

> Sorry for being vague. NMF indeed tends to generally return sparse 
> representations. I meant sparse NMF as in an implementation of NMF that can 
> take sparse matrices as inputs (effectively keeping either the larger of W, H 
> or both as sparse matrices)

Ah ok, you meant sparse input ;-)

(If you need to update W and H often, keeping them in sparse format
seems to be hard to me...)

> The big picture is that the plain_sgd with non_negative flag will add 
> flexibility to more  algorithms, right?

I guess it could be used to do SGD-based NMF.

Mathieu

------------------------------------------------------------------------------
Try before you buy = See our experts in action!
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-dev2
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general

Reply via email to