Uploaded image for project: 'Spark'
  1. Spark
  2. SPARK-3181

Add Robust Regression Algorithm with Huber Estimator

    XMLWordPrintableJSON

Details

    • New Feature
    • Status: Resolved
    • Major
    • Resolution: Fixed
    • 2.2.0
    • 2.3.0
    • ML

    Description

      Linear least square estimates assume the error has normal distribution and can behave badly when the errors are heavy-tailed. In practical we get various types of data. We need to include Robust Regression to employ a fitting criterion that is not as vulnerable as least square.

      In 1973, Huber introduced M-estimation for regression which stands for "maximum likelihood type". The method is resistant to outliers in the response variable and has been widely used.

      The new feature for MLlib will contain 3 new files
      /main/scala/org/apache/spark/mllib/regression/RobustRegression.scala
      /test/scala/org/apache/spark/mllib/regression/RobustRegressionSuite.scala
      /main/scala/org/apache/spark/examples/mllib/HuberRobustRegression.scala

      and one new class HuberRobustGradient in
      /main/scala/org/apache/spark/mllib/optimization/Gradient.scala

      Attachments

        Issue Links

          Dependent

          Improvement - An improvement or enhancement to an existing feature or task. SPARK-22810 PySpark supports LinearRegression with huber loss

          • Major - Major loss of function.
          • Resolved
          depends upon

          Improvement - An improvement or enhancement to an existing feature or task. SPARK-16494 Upgrade breeze version to 0.12

          • Minor - Minor loss of function, or other problem where easy workaround is present.
          • Resolved
          is related to

          Sub-task - The sub-task of the issue SPARK-32060 Huber loss Convergence

          • Minor - Minor loss of function, or other problem where easy workaround is present.
          • Resolved

          Improvement - An improvement or enhancement to an existing feature or task. SPARK-16592 Improving ml.Logistic Regression on speed and scalability

          • Major - Major loss of function.
          • Resolved
          relates to

          New Feature - A new feature of the product, which has yet to be developed. SPARK-23482 R support for robust regression with Huber loss

          • Major - Major loss of function.
          • Open
          links to

          Pull request #2096 [Github] Pull Request #2096 (fjiang6)

          Pull request #7722 [Github] Pull Request #7722 (fjiang6)

          Pull request #8013 [Github] Pull Request #8013 (fjiang6)

          Pull request #14326 [Github] Pull Request #14326 (yanboliang)

          Pull request #19020 [Github] Pull Request #19020 (yanboliang)

          Activity

            People

              yanboliang Yanbo Liang
              fjiang6 Fan Jiang
              DB Tsai DB Tsai
              Votes:
              0 Vote for this issue
              Watchers:
              13 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: