Keywords: Deterministic Denoising Diffusion
TL;DR: Deriving a deterministic denoising diffusion with very basic concepts (no langevin equation, no score, etc.)
Abstract: We present a learning method that produces a mapping between arbitrary densities, such that random samples of a density can be mapped to random samples of another. In practice, our method is similar to deterministic diffusion processes where samples of the target density are blended with Gaussian noise. The originality of our approach is that, in contrast to several recent works, we do not rely on Langevin dynamics or score-matching concepts. We propose a simpler take on the topic, which is based solely on Bayes' theorem. By studying blended samples and their posteriors, we show that iteratively blending and deblending samples produces random paths between arbitrary densities. We prove that, for finite-variance densities, these paths converge towards a deterministic mapping that can be learnt with a neural network trained to deblend samples. Our method can thus be seen as a generalization of deterministic denoising diffusion where, instead of learning to denoise Gaussian noise, we learn to deblend arbitrary data.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Supplementary Material: zip
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Generative models