University of Sharjah
The authors introduce stochastic variational inference for Gaussian process models. This enables the application of Gaussian Process (GP) models to data sets containing millions of data points. They show how GPs can be variationally decomposed to depend on a set of globally relevant inducing variables which factorize the model in the necessary manner to perform variational inference. Their approach is readily extended to models with non-Gaussian likelihoods and latent variable models based around Gaussian processes. They demonstrate the approach on a simple toy problem and two real world data sets.