[
https://issues.apache.org/jira/browse/SPARK-7222?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
DB Tsai updated SPARK-7222:
---------------------------
Description: Added detailed mathematical derivation of how scaling and
LeastSquaresAggregator work. Also refactored the code so the model is
compressed based on the storage. We may try compress based on the prediction
time. TODO: Add test that fail the test when the correction terms are not
correctly computed. (was: Added detailed mathematical derivation of how
scaling and LeastSquaresAggregator work. Also refactored the code. TODO: Add
test that fail the test when the correction terms are not correctly computed.)
> Added mathematical derivation in comment and compressed the model to
> LinearRegression with ElasticNet
> -----------------------------------------------------------------------------------------------------
>
> Key: SPARK-7222
> URL: https://issues.apache.org/jira/browse/SPARK-7222
> Project: Spark
> Issue Type: Improvement
> Components: ML
> Reporter: DB Tsai
>
> Added detailed mathematical derivation of how scaling and
> LeastSquaresAggregator work. Also refactored the code so the model is
> compressed based on the storage. We may try compress based on the prediction
> time. TODO: Add test that fail the test when the correction terms are not
> correctly computed.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
