[
https://issues.apache.org/jira/browse/SPARK-21131?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Hyukjin Kwon updated SPARK-21131:
---------------------------------
Labels: bulk-closed (was: )
> Fix batch gradient bug in SVDPlusPlus
> -------------------------------------
>
> Key: SPARK-21131
> URL: https://issues.apache.org/jira/browse/SPARK-21131
> Project: Spark
> Issue Type: Bug
> Components: GraphX
> Affects Versions: 2.1.1
> Reporter: ruiqiangfan
> Priority: Major
> Labels: bulk-closed
>
> I think the mode of batch gradient in Graphx SVDPlusPlus is incorrect. The
> changes of this pull request are as blow:
> * Use the mean of batch gradient instead of the sum of batch gradient.
> * When calculating the residual of each rating during iteration, the pred
> value shouldn't be limit in (minVal, maxVal).
> * The method "calculateIterationRMSE" is added to show the iteration effect
> clearly.
> I test SVDPlusPlus locally by using movielens-100k dataset. The RMSE of
> origin SVDPlusPlus can't get converged and looks completely wrong. The RMSE
> of new SVDPlusPlus gets converged correctly.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
