On Wed, Oct 19, 2011 at 6:32 PM, Lars Buitinck <[email protected]> wrote:

> I was wondering what the LogisticRegression class in
> sklearn.linear_modules implements. Its docstring says just "logistic
> regression", but I stumbled upon the liblinear authors' paper on LR
> [1], and they claim to have developed a fast multiclass LR/MaxEnt
> training algorithm as well. Does our implementation do LR or ME?

Liblinear (at least the version we're shipping) uses one-vs-all LR. To
see that, have a look at the train routine in linear.cpp and you'll
see that it does a one-vs-all except when param->solver_type ==
MCSVM_CS, which corresponds to the multiclass SVM formulation of
Crammer and Singer.

Mathieu

------------------------------------------------------------------------------
All the data continuously generated in your IT infrastructure contains a
definitive record of customers, application performance, security
threats, fraudulent activity and more. Splunk takes this data and makes
sense of it. Business sense. IT sense. Common sense.
http://p.sf.net/sfu/splunk-d2d-oct
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general

Reply via email to