Deep Horseshoe Gaussian Processes

arXiv:2403.01737v1 Announce Type: cross
Abstract: Deep Gaussian processes have recently been proposed as natural objects to fit, similarly to deep neural networks, possibly complex features present in modern data samples, such as compositional structures. Adopting a Bayesian nonparametric approach, it is natural to use deep Gaussian processes as prior distributions, and use the corresponding posterior distributions for statistical inference. We introduce the deep Horseshoe Gaussian process Deep-HGP, a new simple prior based on deep Gaussian processes with a squared-exponential kernel, …

abstract arxiv bayesian data features gaussian processes math.st modern natural networks neural networks objects posterior prior processes samples stat.ml stat.th type