Github user jkbradley commented on the pull request:
https://github.com/apache/spark/pull/4259#issuecomment-87094307
@dbtsai That sounds reasonable. I think we could do a general
implementation based on abstractions for regularization and loss functions, but
it might not be as efficient as specializations (such as closed-form
computation of the intercept for linear regression). I'm OK with this for now,
and I definitely support comparisons with R for correctness.
Let me know when it's all ready so I can make a detailed pass!
---
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]
