2013/1/31 Satrajit Ghosh <sa...@mit.edu>: > hi all, > > i have been playing with the discretize option in spectral clustering and it > seems to be quite sensitive to the random state. > > here is demo with the sklearn demo (just iterating over 4 random states): > > https://dl.dropbox.com/u/363467/test_discretize.ipynb > > i haven't read the literature behind it, but i thought i would ask if this > is the expected behavior? or if there were any thoughts on the list.
All the solutions look qualitatively as good as one another to me: http://nbviewer.ipython.org/urls/dl.dropbox.com/u/363467/test_discretize.ipynb I would say that this is just an issue of the many good local optima this problem has, not an issue with the algorithm itself. -- Olivier http://twitter.com/ogrisel - http://github.com/ogrisel ------------------------------------------------------------------------------ Everyone hates slow websites. So do we. Make your web apps faster with AppDynamics Download AppDynamics Lite for free today: http://p.sf.net/sfu/appdyn_d2d_jan _______________________________________________ Scikit-learn-general mailing list Scikit-learn-general@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
