Back to Search Start Over

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

Authors :
Neyshabur, Behnam
Bhojanapalli, Srinadh
Srebro, Nathan
Publication Year :
2017

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.<br />Comment: Accepted to ICLR 2018

Subjects

Subjects :
Computer Science - Learning

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.1707.09564
Document Type :
Working Paper

Tools

Authors Abstract Subjects Details