Export Reviews, Discussions, Author Feedback and Meta-Reviews

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The authors present a flexible variational inference method geared Gaussian process models with various likelihoods. Specifically, they derive an inference method for models where some fixed number of latent functions (with GP priors that depend on the input covariate) parameterize a likelihood for conditionally independent observations. They use variational inference to obtain the posterior over the latent functions, where the variational family of distributions is taken to be a mixture of Gaussians with some fixed number of components, and some covariance complexity (full, diagonal, block diagonal, etc). The paper derives the standard evidence lower bound (ELBO), which decomposes into a negative KL term and an expected log-likelihood term, and they note some convenient properties of these decompositions (re: optimizing covariance function parameters). This paper is well written, very clear, and technically sound.