Cool. I previously potted and tested the qr decomposition. Looks I have a similar task ahead for the svd.
It us the convention that the singular values come out in order but there is usually no guarantee that the will so the svd codes usually have a sort step to do this. Sent from my iPhone On Oct 9, 2010, at 10:09 PM, "Dmitriy Lyubimov (JIRA)" <[email protected]> wrote: > > [ > https://issues.apache.org/jira/browse/MAHOUT-376?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12919567#action_12919567 > ] > > Dmitriy Lyubimov edited comment on MAHOUT-376 at 10/10/10 1:08 AM: > ------------------------------------------------------------------- > > ok, i got to BBt normalized for rank deficiences in Q blocks. > > What eigensolver should i use in context of Mahout? I know there's something > in that Cern library but it is all deprecateed. There's also a solver in > apache commons, but it is not readily imported into the mahout core. > > Thanks. > > PS. i tried EigenvalueDecomposition from cern library. I know i am quite > likely providing an ill-conditioned matrix in my unit test but strange thing > is that eigen values are not always in descending order. i thought they were > supposed to come out in descending order? > > was (Author: dlyubimov2): > ok, i got to BBt normalized for rank deficiences in Q blocks. > > What eigensolver should i use in context of Mahout? I know there's something > in that Cern library but it is all deprecateed. There's also a solver in > apache commons, but it is not readily imported into the mahout core. > > Thanks. > >> 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, sd-bib.bib, sd.pdf, 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. >
