Recently the generalization error of deep neural networks has been analyzed through the PAC-Bayesian framework, for the case of fully connected layers. We adapt this approach to the convolutional setting.
@article{arxiv.1801.00171,
title = {PAC-Bayesian Margin Bounds for Convolutional Neural Networks},
author = {Konstantinos Pitas and Mike Davies and Pierre Vandergheynst},
journal= {arXiv preprint arXiv:1801.00171},
year = {2018}
}
Comments
arXiv admin note: text overlap with arXiv:1707.09564 by other authors