TensorFlow Boosted Trees (TFBT) is an improved scalable ensemble model built on top of generic gradient boosting trees.
Google published the details of the TensorFlow boosted trees implementation in the following paper: A scalable TensorFlow based framework for gradient boosting by Natalia Ponomareva, Soroush Radpour, Gilbert Hendry, Salem Haykal, Thomas Colthurst, Petr Mitrichev, Alexander Grushetsky, presented at the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD) 2017. The paper is available at the following link: http://ecmlpkdd2017.ijs.si/papers/paperID705.pdf.
The gradient boosting algorithm is implemented by various libraries such ...