You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@spark.apache.org by "Joseph K. Bradley (JIRA)" <ji...@apache.org> on 2016/07/25 21:03:20 UTC

[jira] [Comment Edited] (SPARK-16718) gbm-style treeboost

    [ https://issues.apache.org/jira/browse/SPARK-16718?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15392662#comment-15392662 ] 

Joseph K. Bradley edited comment on SPARK-16718 at 7/25/16 9:03 PM:
--------------------------------------------------------------------

Also, it'd be nice to compare with an existing implementation.  E.g., if we can compare with R gbm, we can add a unit test doing that, following a few other unit tests in spark.ml.


was (Author: josephkb):
Also, it'd be nice to compare with an existing implementation.  E.g., if we can compare with R gbm, we can add a unit test doing that, following a few other unit tests in spark.ml.

Note: [~vlad.feinberg] is working on this now.

> gbm-style treeboost
> -------------------
>
>                 Key: SPARK-16718
>                 URL: https://issues.apache.org/jira/browse/SPARK-16718
>             Project: Spark
>          Issue Type: Sub-task
>          Components: MLlib
>            Reporter: Vladimir Feinberg
>            Assignee: Vladimir Feinberg
>
> As an initial minimal change, we should provide TreeBoost as implemented in GBM for both L1 and L2 losses: by introducing a new "loss-based" impurity, tree leafs in GBTs can have loss-optimal predictions for their partition of the data.
> Commit should have evidence of accuracy improvment



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org