[mlpack-git] [mlpack/mlpack] Density Estimation Tree made sparse-enabled (#802)

[Ryan Curtin]

> One general comment - as can be seen - I'm making some performance tests with real data and it turns the sparse matrix performance is tremendously worse - specifically in extracting the values to be sorted and then checked. I'm continuing my experiments but, I guess this should not stop the PR merge.

I am not surprised... the CSC sparse matrix format turns out to only be useful for linear algebra operations in extremely sparse matrices.  In the future I think Armadillo should replace its implementation of CSC with coordinate list format sparse matrices... since I wrote the CSC support, this task should fall to me, but I have not done it yet... :)

-- 
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/pull/802#issuecomment-256214017
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20161025/6a58fcb9/attachment.html>