Star algorithm for NN ensembling
Machine Learning
2022-06-02 v1 Statistics Theory
Statistics Theory
Abstract
Neural network ensembling is a common and robust way to increase model efficiency. In this paper, we propose a new neural network ensemble algorithm based on Audibert's empirical star algorithm. We provide optimal theoretical minimax bound on the excess squared risk. Additionally, we empirically study this algorithm on regression and classification tasks and compare it to most popular ensembling methods.
Cite
@article{arxiv.2206.00255,
title = {Star algorithm for NN ensembling},
author = {Sergey Zinchenko and Dmitry Lishudi},
journal= {arXiv preprint arXiv:2206.00255},
year = {2022}
}