Deep Neural Networks as Point Estimates for Deep Gaussian Processes

Abstract

Neural networks and Gaussian processes are complementary in their strengths and weaknesses. Having a better understanding of their relationship comes with the promise to make each method benefit from the strengths of the other. In this work, we establish an equivalence between the forward passes of neural networks and (deep) sparse Gaussian process models. The theory we develop is based on interpreting activation functions as interdomain inducing features through a rigorous analysis of the interplay between activation functions and kernels. This results in models that can either be seen as neural networks with improved uncertainty prediction or deep Gaussian processes with increased prediction accuracy. These claims are supported by experimental results on regression and classification datasets.

35th Conference on Neural Information Processing Systems (NeurIPS 2021)

References in corpus (9)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Scalable Variational Gaussian Process Classification
• Random Feature Expansions for Deep Gaussian Processes
• A Framework for Interdomain and Multioutput Gaussian Processes
• Nested Variational Compression in Deep Gaussian Processes
• Sparse Gaussian Processes with Spherical Harmonic Features
• A Tutorial on Sparse Gaussian Processes and Variational Inference
• GPflux: A Library for Deep Gaussian Processes
• Inter-domain Deep Gaussian Processes