Where can we find almond trees?

How does one find the optimal value for the tuning parameters in boosting trees?

• I realise that there are 3 tuning parameters in the boosting trees model, i.e. the number of trees (number of iterations) shrinkage parameter number of splits (size of the constituent trees) My question is: for each of the tuning parameters, how should I find its optimal value ? And what method ? Note that: the shrinkage parameter and the number of trees parameter operate together, i.e. a smaller value for shrinkage parameter leads to a higher value for the number of trees. And we need to take this into account too. I am particularly interested in the method to find the optimal value for the number of splits. Should it be based on cross-validation or domain knowledge about the model behind? And how are these things carried out in the gbm package in R ?

• Answer:

  You may find these model selection and evaluation methods helpful: grid search, pipeline and feature union. Python users can refer to http://scikit-learn.org/stable/model_selection.html