What makes gradient boosting different from bagging?

Question: What is a key difference between boosting and bagging? A) Bagging trains models sequentially, while boosting trains all models independently B) Boosting trains weak learners sequentially, with later learners correcting earlier errors C) Boosting never uses loss functions D) Bagging always uses neural networks Correct: B Explanation: In boosting, each new learner is trained to improve on the mistakes or residuals of the previous ensemble. Bagging trains models more independently, usually on bootstrap samples, and averages their predictions. Topic: advanced ML / ensemble learning / boosting