arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.09084stat.MLcs.LG
收藏

算子信息得分匹配用于马尔可夫扩散模型

Operator-Informed Score Matching for Markov Diffusion Models

Newcastle University(新castle大学);King’s College London(伦敦国王学院);The Alan Turing Institute(艾伦·图灵研究所)

Zheyang Shen, Huihui Wang, Marina Riabiz, Chris J. Oates

AI总结:

本文提出算子信息得分匹配方法,利用马尔可夫加噪过程的谱分解,仅用数据样本均值同时估计所有边际分布的得分函数,为低维生成提供独立方法,并改进高维神经得分估计器。

摘要:

扩散模型通常使用得分匹配进行训练,这是一种学习目标,与指导模型的底层加噪过程无关。本文认为,马尔可夫加噪过程相对于其他替代方案具有优势,因为控制加噪过程的马尔可夫算子已被充分理解。具体而言,通过利用马尔可夫加噪过程的无穷小生成元的谱分解,我们仅使用关于数据分布的样本平均值,即可同时获得所有边际分布的得分函数的参数估计。由此产生的算子信息得分匹配既为低维分布的样本生成提供了一种独立方法,也为高维设置中更好的信息神经得分估计器提供了配方。

英文摘要:

Diffusion models are typically trained using score matching, a learning objective agnostic to the underlying noising process that guides the model. This paper argues that Markov noising processes enjoy an advantage over alternatives, as the Markov operators that govern the noising process are well-understood. Specifically, by leveraging the spectral decomposition of the infinitesimal generator of the Markov noising process, we obtain parametric estimates of the score functions simultaneously for all marginal distributions, using only sample averages with respect to the data distribution. The resulting operator-informed score matching provides both a standalone approach to sample generation for low-dimensional distributions, as well as a recipe for better informed neural score estimators in high-dimensional settings.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑