Gradient Boosting Neural Networks: GrowNet

Sarkhan Badirli, Xuanqing Liu, Zhengming Xing, Avradeep Bhowmik, Khoa D Doan, Sathiya Keerthi

Keywords: Deep Neural Networks, Gradient Boosting classifiers, NN architecture optimization

Abstract: A novel gradient boosting framework is proposed where shallow neural networks are employed as ``weak learners''. General loss functions are considered under this unified framework with specific examples presented for classification, regression and learning to rank. A fully corrective step is incorporated to remedy the pitfall of the greedy function approximation of the classic gradient boosting decision tree. The proposed model rendered outperforming results against state-of-the-art boosting methods in all three tasks on multiple datasets. An ablation study is performed to shed light on the effect of each model component and model hyperparameters.

One-sentence Summary: Neural Network based gradient boosting algorithm to perform multiple tasks.

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2002.07971/code)