提出二项流模型，统一离散有序数据的去噪、采样与似然估计。
Binomial flows: Denoising and flow matching for discrete ordinal data
- 基于二项分布构建离散扩散模型，实现去噪与采样统一
- 在真实数据集上获得可比性能，支持精确似然计算
- 适用于离散非负有序数据，如评分、计数等场景
连续空间中的基于流生成模型利用Tweedie公式将训练时学习的去噪器表示为采样时使用的得分函数。然而，在离散设置中这一关系长期缺失，现有方法多聚焦于学习离散得分和速率。本文针对离散非负有序数据，提出二项流（Binomial flows）框架，填补该空白。该框架提供了一种简单的训练离散扩散模型的方法，能同时实现去噪、采样与精确似然估计。我们在合成数据和真实数据集上验证了方法的有效性，结果表明其具有竞争力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。