This repository contains the JAX implementation that accompanies the paper Probabilistic programming with programmable variational inference, as well as the experiments used to generate figures and ...
Variational inference is a family of optimisation-based methods for approximating complex posterior distributions in Bayesian models. By transforming inference into an optimisation problem, these ...
from scratch in PyTorch. self-contained: no GPflow/GPyTorch. model: y = f_L(...f_2(f_1(x))) + eps, each f_l a sparse GP. inference: sample-through-the-layers variational inference.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results