[mlpack-git] [mlpack/mlpack] GammaDistribution Implementation is Incomplete (#733)

[Ryan Curtin]

@aditya1315: yes, I agree that your approach is reasonable.  You can base the code on what I wrote, and then write some tests for it.  The testing will be the hard part though, I suspect. :)

I wonder if the NaN values for the test are the result of zero values being passed to the training of the distribution.  The Gamma distribution can't handle zero-valued observations (its PDF is 0 at x=0).

-- 
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/issues/733#issuecomment-247061329
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20160914/ea612884/attachment.html>