Analyzing Diffusion as Serial Reproduction. (arXiv:2209.14821v1 [cs.LG])

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 …

arxiv diffusion