A generalized decision tree ensemble based on the NeuralNetworks architecture: Distributed Gradient Boosting Forest (DGBF)

Abstract

Tree ensemble methods have become one of the most successful and widely-used algorithms in machine learning to model discrete or tabular data in a variety in both academia and industry [1,2]. One of the reasons is that they are built on CART model [3], which is a global approximator function (i.e. it is able to approximate any non-stochastic function in José Alberto Benítez-Andrades and María Teresa García-Ordás contributed equally to this work.