Convolutional Deep Kernel Machines

Edward Milsom*, Ben Anson*, Laurence Aitchison*

*Corresponding author for this work

Research output: Working paperPreprint

8 Downloads (Pure)


Standard infinite-width limits of neural networks sacrifice the ability for intermediate layers to learn representations from data. Recent work (A theory of representation learning gives a deep generalisation of kernel methods, Yang et al. 2023) modified the Neural Network Gaussian Process (NNGP) limit of Bayesian neural networks so that representation learning is retained. Furthermore, they found that applying this modified limit to a deep Gaussian process gives a practical learning algorithm which they dubbed the deep kernel machine (DKM). However, they only considered the simplest possible setting: regression in small, fully connected networks with e.g. 10 input features. Here, we introduce convolutional deep kernel machines. This required us to develop a novel inter-domain inducing point approximation, as well as introducing and experimentally assessing a number of techniques not previously seen in DKMs, including analogues to batch normalisation, different likelihoods, and different types of top-layer. The resulting model trains in roughly 77 GPU hours, achieving around 99% test accuracy on MNIST, 72% on CIFAR-100, and 92.7% on CIFAR-10, which is SOTA for kernel methods.
Original languageEnglish
Publication statusPublished - 18 Sept 2023

Bibliographical note

ICLR 2024 Camera Ready Version


  • stat.ML
  • cs.LG


Dive into the research topics of 'Convolutional Deep Kernel Machines'. Together they form a unique fingerprint.

Cite this