223 citations · 727 across the 52 of their papers we have counts for
Showing 2022 · stat.MLShow all
2 papers · 2 filters
stat.ML2022★ 22 cited
GENIE: Higher-Order Denoising Diffusion Solvers
Tim Dockhorn, Arash Vahdat, Karsten Kreis
Denoising diffusion models (DDMs) have emerged as a powerful class of generative models. A forward diffusion process slowly perturbs the data, while a deep model learns to graduall…
stat.ML2022★ 21 cited
Differentially Private Diffusion Models
Tim Dockhorn, Tianshi Cao, Arash Vahdat +1
While modern machine learning models rely on increasingly large training datasets, data is often limited in privacy-sensitive domains. Generative models trained with differential p…