Uploaded image for project: 'Spark'
  1. Spark
  2. SPARK-4583

GradientBoostedTrees error logging should use loss being minimized

Attach filesAttach ScreenshotVotersWatch issueWatchersCreate sub-taskLinkCloneUpdate Comment AuthorReplace String in CommentUpdate Comment VisibilityDelete Comments
    XMLWordPrintableJSON

Details

    • Improvement
    • Status: Resolved
    • Minor
    • Resolution: Fixed
    • 1.2.0
    • 1.2.0
    • MLlib
    • None

    Description

      Currently, the LogLoss used by GradientBoostedTrees has 2 issues:

      • the gradient (and therefore loss) does not match that used by Friedman (1999)
      • the error computation uses 0/1 accuracy, not log loss

      Attachments

        Activity
          This comment will be Viewable by All Users Viewable by All Users
          Cancel

          People

            josephkb Joseph K. Bradley
            josephkb Joseph K. Bradley
            Votes:
            0 Vote for this issue
            Watchers:
            3 Start watching this issue

            Dates

              Created:
              Updated:
              Resolved:

              Slack

                Issue deployment