DeepAI AI Chat
Log In Sign Up

Deep Neural Networks as Point Estimates for Deep Gaussian Processes

by   Vincent Dutordoir, et al.

Deep Gaussian processes (DGPs) have struggled for relevance in applications due to the challenges and cost associated with Bayesian inference. In this paper we propose a sparse variational approximation for DGPs for which the approximate posterior mean has the same mathematical structure as a Deep Neural Network (DNN). We make the forward pass through a DGP equivalent to a ReLU DNN by finding an interdomain transformation that represents the GP posterior mean as a sum of ReLU basis functions. This unification enables the initialisation and training of the DGP as a neural network, leveraging the well established practice in the deep learning community, and so greatly aiding the inference task. The experiments demonstrate improved accuracy and faster training compared to current DGP methods, while retaining favourable predictive uncertainties.


page 10

page 11


Approximate Inference Turns Deep Networks into Gaussian Processes

Deep neural networks (DNN) and Gaussian processes (GP) are two powerful ...

Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processes

Variational inference is a popular approach to reason about uncertainty ...

On the expected behaviour of noise regularised deep neural networks as Gaussian processes

Recent work has established the equivalence between deep neural networks...

Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks

The point estimates of ReLU classification networks—arguably the most wi...

Rate Optimal Variational Bayesian Inference for Sparse DNN

Sparse deep neural network (DNN) has drawn much attention in recent stud...

Reducing the Amortization Gap in Variational Autoencoders: A Bayesian Random Function Approach

Variational autoencoder (VAE) is a very successful generative model whos...

GPflux: A Library for Deep Gaussian Processes

We introduce GPflux, a Python library for Bayesian deep learning with a ...