揭示生成模型中噪声数据与目标预测的相关性弱点
Correlation Analysis of Generative Models
- 用两个线性方程统一建模扩散模型与流匹配
- 理论证明现有模型中噪声数据与目标相关性常较弱
- 为改进生成模型的训练稳定性提供理论依据
本文基于对现有扩散模型与神经网络流匹配方法的文献综述，提出一种统一表示方法，通过两个简单的线性方程刻画这些模型。进一步进行理论分析表明，现有扩散模型与流匹配中，噪声数据与预测目标之间的相关性有时较弱，这可能影响所有模型中的预测（或学习）过程，而该过程在模型中起着关键作用。
原文摘要 · Abstract (English)
Based on literature review about existing diffusion models and flow matching with a neural network to predict a predefined target from noisy data, a unified representation is first proposed for these models using two simple linear equations in this paper. Theoretical analysis of the proposed model is then presented. Our theoretical analysis shows that the correlation between the noisy data and the predicted target is sometimes weak in the existing diffusion models and flow matching. This might affect the prediction (or learning) process which plays a crucial role in all models.
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。