The limits to learning a diffusion model
Generative Models
Machine Learning
Deep Learning
Read transcript · Original paper
AI-generated voices discussing a paper selected by Arjun Srivastava.
About this paper
Don’t be confused by the title, diffusion here is not referring to diffusion as we use it today in context of image generation process, but more about modelling diffusive processes (like virus spread)
This paper answers the question about ‘how much data do we need, before we can figure out the final affected value’ turns out this is a lot more thant people expect.