The coupling effect of Lipschitz regularization in deep neural networks
Machine Learning
2019-04-15 v1 Machine Learning
Abstract
We investigate robustness of deep feed-forward neural networks when input data are subject to random uncertainties. More specifically, we consider regularization of the network by its Lipschitz constant and emphasize its role. We highlight the fact that this regularization is not only a way to control the magnitude of the weights but has also a coupling effect on the network weights accross the layers. We claim and show evidence on a dataset that this coupling effect brings a tradeoff between robustness and expressiveness of the network. This suggests that Lipschitz regularization should be carefully implemented so as to maintain coupling accross layers.
Cite
@article{arxiv.1904.06253,
title = {The coupling effect of Lipschitz regularization in deep neural networks},
author = {Nicolas Couellan},
journal= {arXiv preprint arXiv:1904.06253},
year = {2019}
}