Adding One Neuron Can Eliminate All Bad Local Minima
Machine Learning
2018-05-23 v1 Machine Learning
Abstract
One of the main difficulties in analyzing neural networks is the non-convexity of the loss function which may have many bad local minima. In this paper, we study the landscape of neural networks for binary classification tasks. Under mild assumptions, we prove that after adding one special neuron with a skip connection to the output, or one special neuron per layer, every local minimum is a global minimum.
Keywords
Cite
@article{arxiv.1805.08671,
title = {Adding One Neuron Can Eliminate All Bad Local Minima},
author = {Shiyu Liang and Ruoyu Sun and Jason D. Lee and R. Srikant},
journal= {arXiv preprint arXiv:1805.08671},
year = {2018}
}