Dependence between Bayesian neural network units
Machine Learning
2021-11-30 v1
Abstract
The connection between Bayesian neural networks and Gaussian processes gained a lot of attention in the last few years, with the flagship result that hidden units converge to a Gaussian process limit when the layers width tends to infinity. Underpinning this result is the fact that hidden units become independent in the infinite-width limit. Our aim is to shed some light on hidden units dependence properties in practical finite-width Bayesian neural networks. In addition to theoretical results, we assess empirically the depth and width impacts on hidden units dependence properties.
Keywords
Cite
@article{arxiv.2111.14397,
title = {Dependence between Bayesian neural network units},
author = {Mariia Vladimirova and Julyan Arbel and Stéphane Girard},
journal= {arXiv preprint arXiv:2111.14397},
year = {2021}
}