A Reparameterization-Invariant Flatness Measure for Deep Neural Networks

Henning Petzka, Linara Adilova, Michael Kamp, Cristian Sminchisescu: A Reparameterization-Invariant Flatness Measure for Deep Neural Networks. Science meets Engineering of Deep Learning workshop at NeurIPS, 2019.

Abstract

BibTeX (Download)

@workshop{petzka2019reparameterization,
title = {A Reparameterization-Invariant Flatness Measure for Deep Neural Networks},
author = {Henning Petzka and Linara Adilova and Michael Kamp and Cristian Sminchisescu},
url = {https://arxiv.org/pdf/1912.00058},
year  = {2019},
date = {2019-01-01},
booktitle = {Science meets Engineering of Deep Learning workshop at NeurIPS},
keywords = {deep learning, flatness, generalization, learning theory, loss surface, neural networks, robustness},
pubstate = {published},
tppubtype = {workshop}
}

Leave a Reply

Your email address will not be published.

This site uses Akismet to reduce spam. Learn how your comment data is processed.