Variational Gaussian Process

Representations offered by deep generative models are fundamentally tied to their inference method from data. Variational inference methods require a rich family of approximating distributions. We construct the variational Gaussian process (VGP), a Bayesian nonparametric model which adapts its shape to match complex posterior distributions. The VGP generates approximate posterior samples by generating latent inputs and warping them through random non-linear mappings; the distribution over random mappings is learned during inference, enabling the transformed outputs to adapt to varying complexity. We prove a universal approximation theorem for the VGP, demonstrating its representative power for learning any model. For inference we present a variational objective inspired by autoencoders and perform black box inference over a wide class of models. The VGP achieves new state-of-the-art results for unsupervised learning, inferring models such as the deep latent Gaussian model and the recently proposed DRAW.