Back to Search Start Over

Wide stochastic networks: Gaussian limit and PAC-Bayesian training

Authors :
Clerico, Eugenio
Deligiannidis, George
Doucet, Arnaud
Source :
The 34th International Conference on Algorithmic Learning Theory (ALT 2023)
Publication Year :
2021

Abstract

The limit of infinite width allows for substantial simplifications in the analytical study of over-parameterised neural networks. With a suitable random initialisation, an extremely large network exhibits an approximately Gaussian behaviour. In the present work, we establish a similar result for a simple stochastic architecture whose parameters are random variables, holding both before and during training. The explicit evaluation of the output distribution allows for a PAC-Bayesian training procedure that directly optimises the generalisation bound. For a large but finite-width network, we show empirically on MNIST that this training approach can outperform standard PAC-Bayesian methods.

Details

Database :
arXiv
Journal :
The 34th International Conference on Algorithmic Learning Theory (ALT 2023)
Publication Type :
Report
Accession number :
edsarx.2106.09798
Document Type :
Working Paper