论文标题
分析扩散作为串行繁殖
Analyzing Diffusion as Serial Reproduction
论文作者
论文摘要
扩散模型是一类生成模型，它们通过颠倒逐渐将数据映射到噪声的扩散过程来学会合成样品。尽管这些模型最近取得了巨大的成功，但对它们观察到的特性的全面理解仍然缺乏，尤其是它们对噪声家族选择的敏感性较弱，以及对噪声水平适当安排良好综合的作用。通过识别传播模型与认知科学中众所周知的范式之间的对应关系，称为序列繁殖，从而使人类的代理迭代观察和从记忆中繁殖刺激，我们表明了如何将扩散模型的上述特性解释为这种对应关系的自然结果。然后，我们通过展示这些关键特征的模拟来补充理论分析。我们的工作强调了认知科学中的经典范式如何阐明最新的机器学习问题。
Diffusion models are a class of generative models that learn to synthesize samples by inverting a diffusion process that gradually maps data into noise. While these models have enjoyed great success recently, a full theoretical understanding of their observed properties is still lacking, in particular, their weak sensitivity to the choice of noise family and the role of adequate scheduling of noise levels for good synthesis. By identifying a correspondence between diffusion models and a well-known paradigm in cognitive science known as serial reproduction, whereby human agents iteratively observe and reproduce stimuli from memory, we show how the aforementioned properties of diffusion models can be explained as a natural consequence of this correspondence. We then complement our theoretical analysis with simulations that exhibit these key features. Our work highlights how classic paradigms in cognitive science can shed light on state-of-the-art machine learning problems.
