Ok, thanks, Jake. let me review the code there and i will write up a jira issue.
(the list keeps rejecting me for spam on every second post of mine :) On Fri, Feb 25, 2011 at 4:01 PM, Jake Mannix <[email protected]> wrote: > Given the way we implement matrix multiplication in DRM, folding in a > rescaling would be very easy to add (the same method could even > extended by being given a Vector of diagonal values, which when null > is ignored). > > Just be careful to multiply it in the correct order (ie make sure you > output > A^t * B * D, not D * A^t * B) - being able to tell which is which inside of > DistributedRowMatrix#times() is tricky. > > -jake > > >
