Seminar: Doubly Stochastic Variational Inference for Deep Gaussian Processes

SpeakerHugh Salimbeni
AffiliationImperial College London
DateFriday, 20 Oct 2017
Time13:00 - 14:00
LocationRoberts Building G08 Sir David Davies LT
Event seriesDeepMind CSML Seminar Series
Description

Gaussian processes (GPs) are a good choice for function approximation as they are flexible, robust to over-fitting, and provide well-calibrated predictive uncertainty. Deep Gaussian processes (DGPs) are multi-layer generalisations of GPs, but inference in these models has proved challenging. Existing approaches to inference in DGP models assume approximate posteriors that force independence between the layers, and do not work well in practice. We present a doubly stochastic variational inference algorithm, which does not force independence between layers. With our method of inference we demonstrate that a DGP model can be used effectively on data ranging in size from hundreds to a billion points. We provide strong empirical evidence that our inference scheme for DGPs works well in practice in both classification and regression.

iCalendar csml_id_323.ics