What does warmstart enable when increasing nestimators in classic GradientBoosting?
Classic MLLevel: IntermediateContinuing an ensemble
What does warm_start enable when increasing n_estimators in classic GradientBoosting?
Hints
- Existing weak learners are retained.
- Continuation is different from a fresh experiment.
Answer
It reuses the existing ensemble and adds stages instead of discarding all fitted trees. It is not a license to change arbitrary training assumptions or treat unrelated datasets as interchangeable.
Source and licence: scikit-learn 1.7.2 — ensemble · BSD-3-Clause · answer: Quantoros editorial