TF Boosted Trees: A scalable TensorFlow based framework for gradient boosting
Machine Learning
2017-11-01 v1 Machine Learning
Abstract
TF Boosted Trees (TFBT) is a new open-sourced frame-work for the distributed training of gradient boosted trees. It is based on TensorFlow, and its distinguishing features include a novel architecture, automatic loss differentiation, layer-by-layer boosting that results in smaller ensembles and faster prediction, principled multi-class handling, and a number of regularization techniques to prevent overfitting.
Keywords
Cite
@article{arxiv.1710.11555,
title = {TF Boosted Trees: A scalable TensorFlow based framework for gradient boosting},
author = {Natalia Ponomareva and Soroush Radpour and Gilbert Hendry and Salem Haykal and Thomas Colthurst and Petr Mitrichev and Alexander Grushetsky},
journal= {arXiv preprint arXiv:1710.11555},
year = {2017}
}
Comments
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2017). The final publication will be available at link.springer.com and is available on ECML website http://ecmlpkdd2017.ijs.si/papers/paperID705.pdf