[jira] [Closed] (MADLIB-777) SVM Regression produces different predictions on multiple runs of the same training and test sets.

["Frank McQuillan (JIRA)" <ji...@apache.org>]

     [ https://issues.apache.org/jira/browse/MADLIB-777?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Frank McQuillan closed MADLIB-777.
----------------------------------
    Resolution: Fixed

Resolved by writing new SVM for scratch for v1.9

Closing this JIRA.

> SVM Regression produces different predictions on multiple runs of the same training and test sets.
> --------------------------------------------------------------------------------------------------
>
>                 Key: MADLIB-777
>                 URL: https://issues.apache.org/jira/browse/MADLIB-777
>             Project: Apache MADlib
>          Issue Type: Bug
>            Reporter: Srivatsan
>            Assignee: Rahul Iyer
>            Priority: Critical
>             Fix For: v1.9
>
>
> I tested this on MADlib 0.7 but I am not sure if this is version specific.
> Attaching the training & test tables (combo_svm_train.sql and combo_svm_dev.sql) and the SQL file to train MADlib's SVM Regression and to predict using the trained model on the dev set.
> Each time you run the training & prediction, you get wildly different prediction results (the R^2 varies between -0.50 to 0.50 in the several attempts that I ran the model).
> Not sure if this is expected behavior or if there is an error I've overlooked. If it is the expected behavior, the models are unusable unless I train the multiple models in parallel and use some sort of voting to minimize the variation. But this seems serious otherwise.



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