Harry Jake Cunningham — accepted AI-conference papers

2025

Infinite Neural Operators: Gaussian processes on functions

Daniel Augusto de Souza, Yuchen Zhu, Harry Jake Cunningham, Yuri Saporito, Diego Mesquita, Marc Peter Deisenroth

NeurIPS 2025poster

A variety of infinitely wide neural architectures (e.g., dense NNs, CNNs, and transformers) induce Gaussian process (GP) priors over their outputs. These relationships provide both an accurate characterization of the prior predictive distribution and enable the use of GP machinery to improve the unc…

Cited by 0 Source ↗Scholar ↗

2024

Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling

Harry Jake Cunningham, Giorgio Giannone, Mingtian Zhang, Marc Peter Deisenroth

NeurIPS 2024poster

Global convolutions have shown increasing promise as powerful general-purpose sequence models. However, training long convolutions is challenging, and kernel parameterizations must be able to learn long-range dependencies without overfitting. This work introduces reparameterized multi-resolution con…

Cited by 1 Source ↗PDF ↗Scholar ↗

2023

Actually Sparse Variational Gaussian Processes

Harry Jake Cunningham, Daniel Augusto de Souza, So Takao, Mark van der Wilk, Marc Peter Deisenroth

AISTATS 2023poster

Gaussian processes (GPs) are typically criticised for their unfavourable scaling in both computational and memory requirements. For large datasets, sparse GPs reduce these demands by conditioning on a small set of inducing variables designed to summarise the data. In practice however, for large data…

Cited by 13 Source ↗PDF ↗code ↗Scholar ↗