Saved in:
Bibliographic Details
Main Authors: Zhang, Leo, Syed, Saifuddin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.04884
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912628802060288
author Zhang, Leo
Syed, Saifuddin
author_facet Zhang, Leo
Syed, Saifuddin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_04884
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Cosine Schedule is Fisher-Rao-Optimal for Masked Discrete Diffusion Models
Zhang, Leo
Syed, Saifuddin
Machine Learning
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.
title The Cosine Schedule is Fisher-Rao-Optimal for Masked Discrete Diffusion Models
topic Machine Learning
url https://arxiv.org/abs/2508.04884