Understanding Diffusion Probabilistic Models (DPMs)

This post was co-written with Baptiste Rocca. Views and opinions expressed are solely those of the authors and do not express the views or opinions of their employers. Unless otherwise noted, all images are by the authors. Modelling complex probability distributions is a central problem in machine learning. If this problem can appear under different shapes, one of the most common setting is the following: given a complex probability distribution only described by some available samples, how can one generates a new sample?