Cambridge, Google & Secondmind’s Neural Diffusion Processes Challenge Gaussian Processes for Describing Rich Distributions Over Functions | Synced

In the new paper Neural Diffusion Processes, a research team from the University of Cambridge, Secondmind, and Google Research presents Neural Diffusion Processes (NDPs), a novel framework that learns to sample from rich distributions over functions at a lower computational cost than the true Bayesian posterior of a conventional Gaussian process.