The Cosine Schedule is Fisher-Rao-Optimal for Masked Discrete Diffusion Models

Leo Zhang, Saifuddin Syed
8/6/2025
stat.MLcs.LG

No confident code implementation found for this paper.

Abstract

In this work, we study the problem of choosing the discretisation schedule for sampling from masked discrete diffusion models in terms of the information geometry of the induced probability path. Specifically, we show that the optimal schedule under the Fisher-Rao geometry recovers the popularly-used cosine schedule.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Cite this paper

@article{zhang2025cosine,
  title  = {The Cosine Schedule is Fisher-Rao-Optimal for Masked Discrete Diffusion Models},
  author = {Leo Zhang and Saifuddin Syed},
  year   = {2025},
  eprint = {2508.04884},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2508.04884v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2508.04884.svg)](https://codeofpaper.com/paper/2508.04884)

Discussion