In scikit-learn implementation of AdaBoost you can choose a learning rate. The documentation about AdaBoost says:
"Learning rate shrinks the contribution of each classifier by learning_rate".
This learning rate is not mentioned anywhere else on AdaBoost tutorials and explanations (for example the official one here http://rob.schapire.net/papers/explaining-adaboost.pdf)
I don't understand this concept of shrinkage of extra trees. Is the learning rate a shrinkage factor, such as 2 means each trees importance is divided by 2? That would be strange as the AdaBoost models learns the importance of each estimator and sample itself.
Thanks for your help!
http://scikit-learn.org/stable/modules/generated/sklearn.ensemble.AdaBoostClassifier.html
