When using gradient boosting in SAS Viya's gbtreetrain CAS action, what does the SUBSAMPLERATE= parameter control?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Here's the deal — b is correct because SUBSAMPLERATE= (also called stochastic gradient boosting or row subsampling) specifies the proportion of training observations randomly drawn for each boosting iteration, reducing variance and helping prevent overfitting. A describes the column subsampling rate (featureImportance/colsampleByTree).
Full explanation below image
Full Explanation
B is correct because SUBSAMPLERATE= (also called stochastic gradient boosting or row subsampling) specifies the proportion of training observations randomly drawn for each boosting iteration, reducing variance and helping prevent overfitting. A describes the column subsampling rate (featureImportance/colsampleByTree). C describes the learning rate / shrinkage parameter. D describes the minimum leaf size parameter.