Computer scienceData scienceMachine learningEnsemble learning

Gradient boosting: the illustrated regression

The selected loss

Report a typo

Why was the squared error loss chosen as the loss function for the example?

Select one option from the list

Because the derivative is the difference between the true target and the prediction, which is convinient

Because the squared error loss is the only loss function applicable in the regression setting for gradient boosting

Because the squared error loss is the most optimal loss function w.r.t. the dataset

___

Create a free account to access the full topic