Trace-class Gaussian priors for Bayesian learning of neural networks with MCMC. (arXiv:2012.10943v3 [stat.ME] UPDATED)

This paper introduces a new neural network based prior for real valued
functions on $\mathbb R^d$ which, by construction, is more easily and cheaply
scaled up in the domain dimension $d$ compared to the usual Karhunen-Lo\`eve
function space prior. The new prior is a Gaussian neural network prior, where
each weight and bias has an independent Gaussian prior, but with the key
difference that the variances decrease in the width of the network in such a
way that the resulting …

arxiv bayesian mcmc networks neural networks