# Stochastic Kernel Regularisation Improves Generalisation in Deep Kernel Machines Source: [Stochastic Kernel Regularisation Improves Generalisation in Deep Kernel Machines]() Collection index: [llms.txt]() Data updated: 2026-01-04T04:54:28.858Z Authors: Edward Milsom, Ben Anson, Laurence Aitchison Published: 2024-10-08T16:15:53.000Z ## Abstract Recent work developed convolutional deep kernel machines, achieving 92.7% test accuracy on CIFAR-10 using a ResNet-inspired architecture, which is SOTA for kernel methods. However, this still lags behind neural networks, which easily achieve over 94% test accuracy with similar architectures. In this work we introduce several modifications to improve the convolutional deep kernel machine's generalisation, including stochastic kernel regularisation, which adds noise to the learned Gram matrices during training. The resulting model achieves 94.5% test accuracy on CIFAR-10. This finding has important theoretical and practical implications, as it demonstrates that the ability to perform well on complex tasks like image classification is not unique to neural networks. Instead, other approaches including deep kernel methods can achieve excellent performance on such tasks, as long as they have the capacity to learn representations from data. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on CIFAR-10 (test)](): Image Classification; CIFAR-10 (test); Accuracy: 94.52. - [Image Classification on CIFAR-100 (test)](): Image Classification; CIFAR-100 (test); Accuracy: not recorded. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()