NeurIPS 2020poster62 citations

Optimization and Generalization of Shallow Neural Networks with Quadratic Activation Functions

Stefano Sarao Mannelli, Eric Vanden-Eijnden, Lenka Zdeborová

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.

BibTeX
@inproceedings{NEURIPS2020_9b8b50fb,
 author = {Sarao Mannelli, Stefano and Vanden-Eijnden, Eric and Zdeborov\'{a}, Lenka},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
 pages = {13445--13455},
 publisher = {Curran Associates, Inc.},
 title = {Optimization and Generalization of Shallow Neural Networks with Quadratic Activation Functions},
 url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/9b8b50fb590c590ffbf1295ce92258dc-Paper.pdf},
 volume = {33},
 year = {2020}
}