A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks

Behnam Neyshabur; Srinadh Bhojanapalli; Nathan Srebro

ICLR 2018poster736 citations

A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks

Behnam Neyshabur, Srinadh Bhojanapalli, Nathan Srebro

Abstract

We present a generalization bound for feedforward neural networks in terms of the product of the spectral norm of the layers and the Frobenius norm of the weights. The generalization bound is derived using a PAC-Bayes analysis.

Neural NetworksGeneralizationPAC-BayesSharpness

BibTeX

@inproceedings{
neyshabur2018a,
title={A {PAC}-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks},
author={Behnam Neyshabur and Srinadh Bhojanapalli and Nathan Srebro},
booktitle={International Conference on Learning Representations},
year={2018},
url={https://openreview.net/forum?id=Skz_WfbCZ},
}