Boosting Machine Learning
noun
Definition: An ensemble-learning method in which weak learners are added sequentially to form a stronger predictor, with each new learner fitted to improve the errors or residuals left by the previous ensemble. Scikit-learn describes AdaBoost as fitting a sequence of weak learners on repeatedly modified versions of the data, and Gradient Boosting as building an additive model in a forward stagewise fashion [scikit-learn Ensemble Documentation].
Example in context: “Additive mixtures of trees, as obtained through bagging or boosting, are tractable, by the linearity of expectation.” [Van den Broeck, Lykov 2022]
Related terms: boosted ensemble, gradient boosting, AdaBoost; contrast term:bagging