On 02/15/2012 12:03 AM, Ian Goodfellow wrote: > I've observed that SVMs fit with sklearn consistently get around 5 > percentage points lower accuracy than equivalent SVMs fit with Adam > Coates' SVM implementation based on minFunc. Am I overlooking some > basic usage issue (eg too loose of a default convergence criterion), > or is this likely to be a defect in the underlying libsvm > implementation? > > To demonstrate, run svm_comparison.m in matlab then svm_comparison.py in > python. > You'll need Adam Coates' code from > http://www.stanford.edu/~acoates/papers/sc_vq_demo.tgz for train_svm > to work. > > To be clear, SVC and Adam Coates' code are supposedly minimizing the > exact same convex loss function, so this really shouldn't happen. > > I would suspect it is caused by the default stopping criterion. Have you tried setting the tolerance higher?
------------------------------------------------------------------------------ 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
