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).

翻译：扩散模型（DMs）是一类强大的生成模型，其通过向数据添加高斯噪声并学习去除噪声来工作。我们试图确定在扩散模型中，哪种噪声分布（高斯或非高斯）能生成更优的数据。由于扩散模型在非高斯噪声下无法按设计运行，我们构建了一个框架，使得能够逆转带有非高斯位置尺度噪声的扩散过程。利用该框架，我们证明了高斯分布在多种分布（拉普拉斯分布、均匀分布、t分布、广义高斯分布）中表现最佳。