NeurIPS 2018poster106 citations
Adding One Neuron Can Eliminate All Bad Local Minima
SHIYU LIANG, Ruoyu Sun, Jason Lee, R. Srikant
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.
BibTeX
@inproceedings{NEURIPS2018_a0128693,
author = {LIANG, SHIYU and Sun, Ruoyu and Lee, Jason D and Srikant, R.},
booktitle = {Advances in Neural Information Processing Systems},
editor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Adding One Neuron Can Eliminate All Bad Local Minima},
url = {https://proceedings.neurips.cc/paper_files/paper/2018/file/a012869311d64a44b5a0d567cd20de04-Paper.pdf},
volume = {31},
year = {2018}
}