Fully Bayesian Autoencoders with Latent Sparse Gaussian Processes

Published in ICML, 2023

Tran, Ba-Hien; Shahbaba, Babak; Mandt, Stephan; Filippone, Maurizio. Fully Bayesian Autoencoders with Latent Sparse Gaussian Processes. International Conference on Machine Learning, 2023.

Autoencoders and their variants are among the most widely used models in representation learning and generative modeling. However, autoencoder-based models usually assume that the learned representations are i.i.d. and fail to capture the correlations between the data samples. To address this issue, we propose a novel Sparse Gaussian Process Bayesian Autoencoder (SGPBAE) model in which we impose fully Bayesian sparse Gaussian Process priors on the latent space of a Bayesian Autoencoder. We perform posterior estimation for this model via stochastic gradient Hamiltonian Monte Carlo. We evaluate our approach qualitatively and quantitatively on a wide range of representation learning and generative modeling tasks and show that our approach consistently outperforms multiple alternatives relying on Variational Autoencoders.

Download paper here