Re:Imagen, a text-to-image diffusion model
by sinenomine on Monday May 23, 2022 @09:19PM
(#31486928)
> It depends on whether you'd like the model to learn casual or correlative relationships.
I expect that in the practical limit of scale achievable, the regularization pressure inherent to the process of training these models converges to https://en.wikipedia.org/wiki/Minimum_description_length and the correlative relationships become optimized away, leaving mostly true causal relationships inherent to data-generating process.
I expect that in the practical limit of scale achievable, the regularization pressure inherent to the process of training these models converges to https://en.wikipedia.org/wiki/Minimum_description_length and the correlative relationships become optimized away, leaving mostly true causal relationships inherent to data-generating process.