Doubly Stochastic Variational Inference for Deep Gaussian Processes

TL;DR

This paper introduces a doubly stochastic variational inference method for deep Gaussian processes that allows for effective inference without assuming layer independence, enabling scalable and accurate modeling for large datasets.

Contribution

The paper presents a novel inference algorithm for DGPs that relaxes layer independence assumptions, improving practical applicability and scalability.

Findings

Effective inference in DGPs on datasets from hundreds to a billion points.

Strong empirical results in classification and regression tasks.

Demonstrates practical utility of the proposed method.

Abstract

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.