A Good Score Does not Lead to A Good Generative Model
CoRR(2024)
摘要
Score-based Generative Models (SGMs) is one leading method in generative
modeling, renowned for their ability to generate high-quality samples from
complex, high-dimensional data distributions. The method enjoys empirical
success and is supported by rigorous theoretical convergence properties. In
particular, it has been shown that SGMs can generate samples from a
distribution that is close to the ground-truth if the underlying score function
is learned well, suggesting the success of SGM as a generative model. We
provide a counter-example in this paper. Through the sample complexity
argument, we provide one specific setting where the score function is learned
well. Yet, SGMs in this setting can only output samples that are Gaussian
blurring of training data points, mimicking the effects of kernel density
estimation. The finding resonates a series of recent finding that reveal that
SGMs can demonstrate strong memorization effect and fail to generate.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要