Bayes4Health research on extending diffusion generative models (co-authored by Arnaud Doucet) was presented as an RSS read paper at the recent Royal Statistical Society Annual Conference in Harrogate.

The paper, "From Denoising Diffusions to Denoising Markov Models” by Benton, Shi, De Bortoli, Deligiannidis and Doucet presents a unified framework for designing generative models with general noising processes. The importance of this work is that it enables the ideas of diffusion generative models to be applied to non-real valued data. This could include discrete data, network, graphs, or e.g. data that is restricted to lie on a manifold.

The paper will appear in the Journal of the Royal Statistical Society, Series B, together with its discussion