Research Colloquium with Botond Szabó (Bocconi University)

We are happy welcome Botond Szabó to give a talk on Deep Vecchia Gaussian Processes

Abstract: Deep Gaussian processes have several advantages compared to standard Gaussian Processes (GPs), including learning local and compositional structures of the signal. However, their practical applicability is hindered by their computational complexity and instability of approximation methods. In this work we propose a novel Vecchia approximation of Deep GPs, derive optimal contraction rates for structured (compositional) functions and discuss algorithmic aspects. We also demonstrate the applicability of the proposed method on synthetic data sets. Based on an ongoing joint work with Ismael Castillo (Sorbonne, Paris), Thibault Randrianarisoa (Vector Institute, Toronto) and Yichen Zhou (University of Hong Kong).

Everyone is cordially invited.