Introduction This is part one of my “Notes on ‘Non-linear PCA” blog article series, where I discuss various deep generative modeling techniques. The series is based on a project that I worked on for Stanford’s CS168, along with Ada Zhou, Chris Rilling, and Devorah Rena Simon. This project was originally titled “Notes on ‘Non-linear PCA’ for Deep Generative Modeling: VAEs, GANs, and DDPMs for Modelling Complex Data Distributions.” Deep generative modelling is a problem that has gained much prominence over the past few years, with the developments of image synthesis services such as OpenAI’s DALLE2 and Stability AI’s Stable Diffusion....