Particle Denoising Diffusion Sampler

Denoising diffusion models have become ubiquitous for generative modeling. The core idea is to transport the data distribution to a Gaussian by using a diffusion. Approximate samples from the data distribution are then obtained by estimating the time-reversal of this diffusion using score matching ideas.

Data and Resources

Cite this as

Angus Phillips, Hai-Dang Dau, Michael John Hutchinson, Valentin De Bortoli, George Deligiannidis, Arnaud Doucet (2024). Dataset: Particle Denoising Diffusion Sampler. https://doi.org/10.57702/08y2pl95

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2402.06320
Author Angus Phillips
More Authors
Hai-Dang Dau
Michael John Hutchinson
Valentin De Bortoli
George Deligiannidis
Arnaud Doucet