DDPMs: Statistical Foundations
Published:
Learning data distribution involves identifying ‘key factors’, which inherently ‘control’ the characteristics of our observations. The controlling relationship can either be statistical, or based on physical laws, where we understand precisely how these factors manifest in data. We discuss these ‘key factors’, commonly referred to as latent variables, in detail below. First, we discuss their estimation from data using Variational Inference (VI). Then, we describe the opposite direction - data reconstruction and generation from latent variables.
