for some day's now I try to implement gradient boosted tree's with flwr. I tried the example given by flwr. They use a LogisticRegression Model for the classification of MNIST, which works in my setup.
This is where my problem arise:
Simply replacing the sklear.linear_model.LogisticRegression model with the sklearn.ensemble.GradientBoostingClassifier does not work because:
I don't know which values I have to initalize, which are equivalent to the LogistiRegression.coef_. Does anyone has an idea?
If I could make a working version I would try to add it to flwr as reference for anybody.
Thanks in advance
