[
https://issues.apache.org/jira/browse/MAHOUT-376?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Ted Dunning updated MAHOUT-376:
-------------------------------
Attachment: sd.tex
sd.pdf
Updates.
I think that the outline of the algorithm is now in place. As it currently
stands, it should scale to
about a thousand cores (maybe more) and should allow very small memory
footprint machines
to participate.
That level should allow us to decompose data in the scale of 1-10 billion
non-zeros, at a guess.
> Implement Map-reduce version of stochastic SVD
> ----------------------------------------------
>
> Key: MAHOUT-376
> URL: https://issues.apache.org/jira/browse/MAHOUT-376
> Project: Mahout
> Issue Type: Improvement
> Components: Math
> Reporter: Ted Dunning
> Assignee: Ted Dunning
> Fix For: 0.5
>
> Attachments: MAHOUT-376.patch, Modified stochastic svd algorithm for
> mapreduce.pdf, sd-bib.bib, sd.pdf, sd.pdf, sd.pdf, sd.tex, sd.tex, sd.tex,
> Stochastic SVD using eigensolver trick.pdf
>
>
> See attached pdf for outline of proposed method.
> All comments are welcome.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
