Does it provide search for optimum fit aka regularization rate? On Mar 19, 2013 8:10 AM, "Sebastian Schelter" <[email protected]> wrote:
> Played a little more with the code, it works astonishingly well. I was > totally off in my expectations. > > I was able to run an iteration of ALS (two map-only jobs) on the Yahoo > Songs dataset (700M interactions) in less than 2 minutes. > > > On 14.03.2013 17:02, Sean Owen wrote: > > On Wed, Mar 13, 2013 at 7:41 PM, Sebastian Schelter <[email protected]> > wrote: > > > >> Hadoop has to reschedule every iteration as separate job, reread the > >> input data from disk and write the iterations result to HDFS. In fact an > >> ALS iteration always includes twice of these things as it needs two M/R > >> jobs. GraphLab/Giraph/Stratosphere on the other hand have to do neither > >> of these three things (GraphLab even doesn't do synchronous iterations) > >> and I highly doubt that a Hadoop implementation can get on par > performance. > >> > > > > That's all true but would you imagine I/O is 97.5% of the run-time? A > > 100-feature vector is 400 bytes, but to compute an update you need to > > invert a 100x100 matrix. I can't see the former taking 40x longer than > the > > latter. That's why I bet you'll find the current implementation is > nothing > > like 40x slower. > > > > 2x? maybe. And 2x is nothing to sneeze at! > > > >
