Skip to content
Sagan

Paper

How Deep Are Deep GPs, Really? A Sharp Threshold and a Non-Gaussian Limit for Compositional GPs

Unreadunread

AI summary

arXiv:2606. 08218v1 Announce Type: cross Abstract: Compositional priors describe the generic properties of layered functions in deep Bayesian models, where deep neural networks with random weights are a canonical example.