notes

Personal notes
git clone git://git.laack.co/notes.git
Log | Files | Refs

HistogramBasedGradientBoosting.md (498B)


      1 # Histogram Based Gradient Boosting (HGB)
      2 
      3 ML D5
      4 
      5 **Definition:** Histogram based gradient boosting is an implementation of gradient boosting that uses binning of input features.
      6 
      7 This is much faster than normal gradient boosting. Also, the normal way of doing this is by rounding to integers for values.
      8 
      9 This is hundreds of times faster in training than gradient boosting on large datasets. At the cost of precision. With that said, binning also acts as a regularizer to help reduce overfitting.