zhengruifeng commented on pull request #29018:
URL: https://github.com/apache/spark/pull/29018#issuecomment-658066066


   @viirya Thanks for reviewing!
   
   > This win only happens when maxBins is less
   
   Yes, but in most cases, maxBin(default=32) < 128
   
   > the perf regression happens for all cases
   
   Yes, I think so.
   
   > I'm also not sure how often memory is an issue when training the model
   
   It will make sense if there is no enough memory for orginal 
treePoint(Array[Int]). I personally think it maybe worthwhile if the regression 
is small enough, but I am not sure whether current performance results are OK.


----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
us...@infra.apache.org



---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org

Reply via email to