具有位置 - 尺度噪声的扩散模型（英文版）

英文标题：Diffusion models with location-scale noise中文摘要：通过研究了不同的噪声分布（高斯分布和非高斯分布），我们发现扩散模型中高斯分布的噪声可以最好地用于生成数据，因此我们可以使用与非高斯噪声相关的扩散过程来确定噪声分布的选择。英文摘要：Diffusion Models (DMs) are powerful generative models that add Gaussian noiseto the data and learn to remove it. We wanted to determine which noisedistribution (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 frameworkthat allows reversing a diffusion process with non-Gaussia