The Renyi Gaussian Process: Towards Improved Generalization

Understand

We introduce an alternative closed form lower bound on the Gaussian process ($\mathcal{GP}$) likelihood based on the R\'enyi $\alpha$-divergence.

• This new lower bound can be viewed as a convex combination of the Nystr\"om approximation and the exact $\mathcal{GP}$.
• The key advantage of this bound, is its capability to control and tune the enforced regularization on the model and thus is a generalization of the traditional variational $\mathcal{GP}$ regression.
• From a theoretical perspective, we provide the convergence rate and risk bound for inference using our proposed approach.