English

Diffusion models with location-scale noise

Machine Learning 2023-04-13 v1 Artificial Intelligence Numerical Analysis Numerical Analysis

Abstract

Diffusion Models (DMs) are powerful generative models that add Gaussian noise to the data and learn to remove it. We wanted to determine which noise distribution (Gaussian or non-Gaussian) led to better generated data in DMs. Since DMs do not work by design with non-Gaussian noise, we built a framework that allows reversing a diffusion process with non-Gaussian location-scale noise. We use that framework to show that the Gaussian distribution performs the best over a wide range of other distributions (Laplace, Uniform, t, Generalized-Gaussian).

Keywords

Cite

@article{arxiv.2304.05907,
  title  = {Diffusion models with location-scale noise},
  author = {Alexia Jolicoeur-Martineau and Kilian Fatras and Ke Li and Tal Kachman},
  journal= {arXiv preprint arXiv:2304.05907},
  year   = {2023}
}
R2 v1 2026-06-28T10:02:20.038Z