Optimization and Generalization of Shallow Neural Networks with Quadratic Activation Functions

Abstract

We study the dynamics of optimization and the generalization properties of one-hidden layer neural networks with quadratic activation function in the overparametrized regime where the layer width m is larger than the input dimension d.

Cite

Text

Mannelli et al. "Optimization and Generalization of Shallow Neural Networks with Quadratic Activation Functions." Neural Information Processing Systems, 2020.

Markdown

[Mannelli et al. "Optimization and Generalization of Shallow Neural Networks with Quadratic Activation Functions." Neural Information Processing Systems, 2020.](https://mlanthology.org/neurips/2020/mannelli2020neurips-optimization/)

BibTeX

@inproceedings{mannelli2020neurips-optimization,
  title     = {{Optimization and Generalization of Shallow Neural Networks with Quadratic Activation Functions}},
  author    = {Mannelli, Stefano Sarao and Vanden-Eijnden, Eric and Zdeborová, Lenka},
  booktitle = {Neural Information Processing Systems},
  year      = {2020},
  url       = {https://mlanthology.org/neurips/2020/mannelli2020neurips-optimization/}
}