Custom Booster of XGBoost (e.g. NN model)

#1

Hi! Thanks for this great support forum.
I was wondering whether is possible to change the base learner of XGBoost.
I would like to apply it to NN, and as an example you can see the work done by Ensemble_pytorch supporting NN model to feed GBoosting.

Thanks in advance.

#2

No, it is currently not possible to change the base learner. There is a feature request open: https://github.com/dmlc/xgboost/issues/5802