[
https://issues.apache.org/jira/browse/SPARK-8536?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14617616#comment-14617616
]
Feynman Liang commented on SPARK-8536:
--------------------------------------
(Rethinking LDA: Why Priors Matter, Wallach 09,
http://dirichlet.net/pdf/wallach09rethinking.pdf) suggests that asymmetric
priors is only useful for the document-topic distribution.
> Generalize LDA to asymmetric priors
> -----------------------------------
>
> Key: SPARK-8536
> URL: https://issues.apache.org/jira/browse/SPARK-8536
> Project: Spark
> Issue Type: Improvement
> Components: MLlib
> Reporter: Joseph K. Bradley
> Original Estimate: 216h
> Remaining Estimate: 216h
>
> Several users have requested LDA using asymmetric priors, including learning
> those hyperparameters. We should add this functionality.
> Note that it could be added to EM, online LDA, or both. I suggest adding it
> to online LDA initially, followed by EM in a separate PR.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
