Boosting is the technique used by GBM.
The ensemble technique used by gradient boosting trees is known as “boosting.” Gradient boosting is an ensemble learning method that combines the predictions of multiple weak learners, typically decision trees, to create a strong predictive model. In the case of gradient boosting trees, each tree is built sequentially, and each subsequent tree corrects the errors made by the previous ones. The process continues until a predefined number of trees are built or no further improvement can be achieved.
So, the correct answer to the question would be “boosting.”