Guardado en:
Detalles Bibliográficos
Autores principales: Shenfeld, Yair, Baptista, Ricardo, Peluchetti, Stefano
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2605.00360
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914524163997696
author Shenfeld, Yair
Baptista, Ricardo
Peluchetti, Stefano
author_facet Shenfeld, Yair
Baptista, Ricardo
Peluchetti, Stefano
contents Flow-based generative modeling in continuous spaces exploit Tweedie's formula to express the denoiser (learned in training) as a score function (used in sampling). In contrast, this relation has been largely missing in the discrete setting where common approaches focus on learning discrete scores and rates. In this work we close this gap for discrete non-negative ordinal data by introducing Binomial flows. Our framework provides a simple recipe for training a discrete diffusion model which simultaneously denoises, samples, and estimates exact likelihoods. We verify our methodology on synthetic examples and obtain competitive results on real-world data sets.
format Preprint
id arxiv_https___arxiv_org_abs_2605_00360
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Binomial flows: Denoising and flow matching for discrete ordinal data
Shenfeld, Yair
Baptista, Ricardo
Peluchetti, Stefano
Machine Learning
Methodology
Flow-based generative modeling in continuous spaces exploit Tweedie's formula to express the denoiser (learned in training) as a score function (used in sampling). In contrast, this relation has been largely missing in the discrete setting where common approaches focus on learning discrete scores and rates. In this work we close this gap for discrete non-negative ordinal data by introducing Binomial flows. Our framework provides a simple recipe for training a discrete diffusion model which simultaneously denoises, samples, and estimates exact likelihoods. We verify our methodology on synthetic examples and obtain competitive results on real-world data sets.
title Binomial flows: Denoising and flow matching for discrete ordinal data
topic Machine Learning
Methodology
url https://arxiv.org/abs/2605.00360