Github user imatiach-msft commented on the issue:
https://github.com/apache/spark/pull/16441
with regards to the loss type, I think the real issue is that the user
shouldn't be able to change the loss type at all on the model, as with many
other parameters. It seems strange to have the model and trainer share the
same parameters in that case. I think you are correct that users will never
change the loss on the model in the future and expect the probability function
to change, but just the fact that they can for some reason and it doesn't
bothers me, but it's not a significant issue.
---
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]
