Github user jkbradley commented on the pull request:
https://github.com/apache/spark/pull/8246#issuecomment-139341684
Considering sparse representations would be nice, though I think that's a
less common use case for trees (vs GLMs). The other (bigger) issue is
communication (which is what my new implementation will address). The main
difference between MLlib and PLANET right now is that MLlib does not switch to
local learning for deep layers of the tree.
For comparing, I'm mainly curious about the total number of nodes in the
tree, just to make sure they are fairly similar.
---
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]
