ICML 2018oral303 citations
On the Power of Over-parametrization in Neural Networks with Quadratic Activation
Abstract
We provide new theoretical insights on why over-parametrization is effective in learning neural networks. For a $k$ hidden node shallow network with quadratic activation and $n$ training data points, we show as long as $ k \ge \sqrt{2n}$, over-parametrization enables local search algorithms to find a
BibTeX
@InProceedings{pmlr-v80-du18a,
title = {On the Power of Over-parametrization in Neural Networks with Quadratic Activation},
author = {Du, Simon and Lee, Jason},
booktitle = {Proceedings of the 35th International Conference on Machine Learning},
pages = {1329--1338},
year = {2018},
editor = {Dy, Jennifer and Krause, Andreas},
volume = {80},
series = {Proceedings of Machine Learning Research},
month = {10--15 Jul},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v80/du18a/du18a.pdf},
url = {https://proceedings.mlr.press/v80/du18a.html},
abstract = {We provide new theoretical insights on why over-parametrization is effective in learning neural networks. For a $k$ hidden node shallow network with quadratic activation and $n$ training data points, we show as long as $ k \ge \sqrt{2n}$, over-parametrization enables local search algorithms to find a