What is the difference between bagging and boosting?

Bagging trains models independently in parallel, while boosting trains models sequentially to correct errors.

Bagging (Bootstrap Aggregation) builds multiple models on different random subsets of data and averages their predictions to reduce variance. Boosting builds models sequentially, where each new model focuses on correcting errors made by previous models, reducing bias. Bagging is robust to overfitting, while boosting is more sensitive but often more accurate.