ICML 2018oral303 citations

On the Power of Over-parametrization in Neural Networks with Quadratic Activation

Simon Du, Jason Lee

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
On the Power of Over-parametrization in Neural Networks with Quadratic Activation · ICML 2018