A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks
published by Behnam Neyshabur
in 2017
in Informatics Engineering
and research's language is
English
Download
Abstract in English
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.