- the no. of small decisions trees(week learns) to use- Unlike random forest, increasing the n_estimators can lead to overfitting
- Typically, these two parameters are tuned together. Since making the learning rates smaller, will require more trees to maintain model complexity.- So typically, the n_estimators setting is chosen to best exploit the speed and memory capabilities of the system during the training. And other parameters like the learning rate are then adjusted, given that fixed an n_estimators setting.