[
https://issues.apache.org/jira/browse/SPARK-8651?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14608847#comment-14608847
]
Joseph K. Bradley commented on SPARK-8651:
------------------------------------------
This seems like an issue for the user list. I doubt it's a bug (but if it is,
please update!). It is probably from needing to use *smaller* step sizes since
your weights are diverging. I'll close this JIRA for now.
> Lasso with SGD not Converging properly
> --------------------------------------
>
> Key: SPARK-8651
> URL: https://issues.apache.org/jira/browse/SPARK-8651
> Project: Spark
> Issue Type: Bug
> Components: MLlib
> Affects Versions: 1.4.0
> Reporter: Albert Azout
>
> We are having issues getting Lasso with SGD to converge properly. The weights
> outputted are extremely large values. We have tried multiple miniBatchRatios
> and still see same issue.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
