AppliedMultiple choice
In gradient boosting, what happens if you halve the learning rate (shrinkage) and double the number of trees?
- ANothing: the two changes cancel exactly
- BUsually slightly better generalisation, at twice the cost
- CGuaranteed overfitting, because more trees always overfit
- DFaster training, because each tree is smaller
The worked solution is in Premium
The answer, the full working and the one idea to take away – for this and all 1,322 questions in the bank. Answer it in practice and your working is marked, with a known mistake named when you make one.
Learn the method
More machine learning questions
- A node holds 40 positive and 60 negative examples. What is its Gini impurity?Foundation
- A node holds 40 positive and 60 negative examples.Foundation
- Scoring a tree split, part 1 of 3Foundation
- Why do gradient-boosted trees usually beat deep networks on daily…Applied
- A node has 50 positives and 50 negatives.Applied
- Scoring a tree split, part 2 of 3Applied