zhengruifeng created SPARK-19208:

             Summary: MaxAbsScaler and MinMaxScaler are very inefficient
                 Key: SPARK-19208
                 URL: https://issues.apache.org/jira/browse/SPARK-19208
             Project: Spark
          Issue Type: Improvement
          Components: ML
            Reporter: zhengruifeng

Now, {{MaxAbsScaler}} and {{MinMaxScaler}} are using 
{{MultivariateOnlineSummarizer}} to compute the min/max.
However {{MultivariateOnlineSummarizer}} will also compute extra unused 
statistics. It slows down the task, moreover it is more prone to cause OOM.

For example:
env : --driver-memory 4G --executor-memory 1G --num-executors 4
data: 748401 instances,   and 3,000,000 features
{{MaxAbsScaler.fit}} fail because OOM

{{MultivariateOnlineSummarizer}} maintain 8 arrays
For {{MaxAbsScaler}}, only one array is needed (max of abs value)
For {{MinMaxScaler}}, only 3 arrays are needed (max, min, nnz)

This message was sent by Atlassian JIRA

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

Reply via email to