BriefGPT.xyz
Jan, 2024
得分高不代表生成模型好
A Good Score Does not Lead to A Good Generative Model
HTML
PDF
Sixu Li, Shi Chen, Qin Li
TL;DR
通过样本复杂性论证，我们在特定设置下展示了得分函数训练良好的情况下，SGM只能输出训练数据点的高斯模糊样本，从而模拟核密度估计的效果，这与最近的研究结果一致，揭示了SGM展示出记忆效应并且无法生成的弱点。
Abstract
score-based generative models
(SGMs) is one leading method in
generative modeling
, renowned for their ability to generate
high-quality samples
→