115f89503138416a242f40fb7d7f338e-Reviews.html

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The paper proposes a variational bound on the length scale parameters of square-exponential-kernel Gaussian process regression models. The main idea is to separate the function to be inferred into a standardised sample from a unit-length-scale square-exponential kernel, and a linear scaling map of that latent function, then to impose factorisation between these two objects via a variational bound. The paper is well written. It uses clear language and provides a compact introduction to previous work.