Supplement to " Learning Individualized Treatment Rules with Many Treatments: A Supervised Clustering Approach Using Adaptive Fusion "

Chapel Hill, NC 27516 haixuma@live.unc.edu A.1 Estimation of the main effect We briefly discuss how to obtain the estimation of the main effect function M For nonparametric regression, we follow [3] to divide the training data into M folds based on the assigned treatment. Then p ErY |Z, A " as is obtained from the regression forest [4] on Y Z with the dataset tpy We refer to [3] for more discussions about the case of misspecifying the main effect, and the corresponding robust and efficient method to solve the misspecification problem. A.2 Implementation details for the adaptive proximal gradient algorithm Recall that U " diagpX U. In addition, we follow [5] to approximately calculate the proximal operator of P The main steps of the proposed algorithm for SCAF are summarized as below.