146f7dd4c91bc9d80cf4458ad6d6cd1b-AuthorFeedback.pdf

Loosely speaking, the margin of apoint depends on the output of the voting classifier,and does not involvethe7 sigmoid function. For base learners, the same size means the same number of leaves (and no restriction on depth for both algorithms37 compared). Inthe supplementalmaterial, submitted along withthe paper,we included the same experiment onthree more data45 sets to give 4 data sets of increasing size to analyze and demonstrate our new theoretical bound on. Themean validation errorandstandard deviation fortheForest Coverdataset47 example from the paper are (0.0298, 0.00037) for LightGBM and (0.0327, 0.00053) for AdaBoost. The standard48 deviation wasso small that we chose toonly show3runs on the plots.