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

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.

ai artificial intelligence cambridge challenge deep-neural-networks diffusion gaussian processes google machine learning machine learning & data science ml processes research technology