[
https://issues.apache.org/jira/browse/MAHOUT-1566?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14014752#comment-14014752
]
Dmitriy Lyubimov edited comment on MAHOUT-1566 at 5/31/14 6:56 PM:
-------------------------------------------------------------------
on implicit feedback issue, i can not just throw it in at the moment because
like i said, it is implemented in bare Spark + scala bindings but porting it to
drm algebra without going native to Spark seems to be a bit of a puzzle at the
moment. I am also contemplating what additional primitives we may formalize in
drm linalg before I resort to falling back to a Spark-coupled method.
was (Author: dlyubimov):
on implicit feedback issue, i can not just throw it in at the moment because
like i said, it is implemented in bare Spark + scala bindings but porting it to
drm without going native to Spark seems to be a bit of a puzzle at the moment.
I am also contemplating what additional primitives we may formalize in drm
linalg before I resort to falling back to a Spark-coupled method.
> Regular ALS factorizer with convergence test.
> ---------------------------------------------
>
> Key: MAHOUT-1566
> URL: https://issues.apache.org/jira/browse/MAHOUT-1566
> Project: Mahout
> Issue Type: Task
> Affects Versions: 0.9
> Reporter: Dmitriy Lyubimov
> Assignee: Dmitriy Lyubimov
> Priority: Trivial
> Fix For: 1.0
>
>
> ALS-related: let's start with unweighed, unregularized implementation.
--
This message was sent by Atlassian JIRA
(v6.2#6252)
