A pier-vendor XGBoost job with a handful of trees underfits; the next run with a huge tree count memorizes last season's sales. Which hyperparameter is that lever?
Select an answer to reveal the explanation.
Short Explanation
Think of an XGBoost job with a handful of trees that underfits, then a huge tree count that memorizes last season. That lever is the number of trees, num_round. Too few underfits, too many overfits.
Full Explanation
On a tree-based model, the number of trees (XGBoost num_round, for example) is the capacity lever: too few underfits and too many overfits. Learning rate is a different hyperparameter. Translate and dropout are not tree-count controls.