2 papers
stat.ML2023
PriorCVAE: scalable MCMC parameter inference with Bayesian deep generative modelling
Elizaveta Semenova, Prakhar Verma, Max Cairney-Leeming +3
Recent advances have shown that GP priors, or their finite realisations, can be encoded using deep generative models such as variational autoencoders (VAEs). These learned generato…
cs.LG2020
VAE: a stochastic process prior for Bayesian deep learning with MCMC
Swapnil Mishra, Seth Flaxman, Tresnia Berah +3
Stochastic processes provide a mathematically elegant way model complex data. In theory, they provide flexible priors over function classes that can encode a wide range of interest…