denoising-diffusion-pytorch
denoising-diffusion-pytorch copied to clipboard
Alpha schedule instead of beta schedule?
In the "Improved Denoising Diffusion Probabilistic Models" paper, the authors claim that cosine schedule of beta makes alpha-bar change more smoothly, leading to better results. Then I wonder why not linearly schedule alpha-bar, instead of beta? We can compute beta from alpha-bar. Anyone tried that?