English

PAC-Bayesian Margin Bounds for Convolutional Neural Networks

Machine Learning 2018-04-24 v2 Machine Learning

Abstract

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.

Keywords

Cite

@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

R2 v1 2026-06-22T23:32:58.910Z