Machine learning
In gradient boosting, what happens if you halve the learning rate (shrinkage)…
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.
Report an issue with this question
Learn the method
More machine learning questions
- A node holds 40 positive and 60 negative examples.Foundation · Premium
- Scoring a tree split, part 1 of 3Foundation · Premium
- Why do gradient-boosted trees usually beat deep networks on daily…Applied · Premium
- A node has 50 positives and 50 negatives.Applied · Premium
- Scoring a tree split, part 2 of 3Applied · Premium
- Two features are nearly identical, and a random forest reports low importance for both.Advanced · Premium