Constant Rate Schedule: Constant-Rate Distributional Change for Efficient Training and Sampling in Diffusion Models

Shuntaro Okada, Kenji Doi, Ryota Yoshihashi, Hirokatsu Kataoka, Tomohiro Tanaka

Keywords: diffusion model, noise schedule

TL;DR: We propose an efficient noise schedule for both training and sampling in diffusion models, leveraging probability-distributional change in the diffusion process.

Abstract:

We propose a noise schedule that ensures a constant rate of change in the probability distribution of diffused data throughout the diffusion process.
To obtain this noise schedule, we measure the rate of change in the probability distribution of the forward process and use it to determine the noise schedule before training diffusion models.
The functional form of the noise schedule is automatically determined and tailored to each dataset and type of diffusion model.
We evaluate the effectiveness of our noise schedule on unconditional and class-conditional image generation tasks using the LSUN (bedroom/church/cat/horse), ImageNet, and FFHQ datasets.
Through extensive experiments, we confirmed that our noise schedule broadly improves the performance of the diffusion models regardless of the dataset, sampler, number of function evaluations, or type of diffusion model.

Primary Area: generative models

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 2420