Github user manishamde commented on the pull request:
https://github.com/apache/spark/pull/2607#issuecomment-61069736
@jkbradley @codedeft I think I have implemented all the suggestions on the
PR except for 1) public API and 2) warning when using non SquaredError loss
functions. I will work on them next.
In the latest version, I have simplified the algorithm implementation and
removed the need for checkpointing since the dataset for each iteration is
calculated using the cached input training dataset and the partial GBT model
till that iteration. I think this implementation will avoid a lot of
checkpointing/caching overhead and lead to a simpler implementation. Could you
please take a look at the logic of ```boost``` method.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
