The Principles of Diffusion Models

About This Book

This book focuses on the principles that have shaped the development of diffusion models, tracing their origins and showing how different formulations arise from common mathematical ideas.

Diffusion modeling begins by specifying a forward corruption process that gradually turns data into noise. This forward process links the data distribution to a simple noise distribution by defining a continuous family of intermediate distributions. The core objective of a diffusion model is to construct another process that runs in the opposite direction, transforming noise into data while recovering the same intermediate distributions defined by the forward corruption process.

Table of Contents

Front Matter

Part A: Introduction to Deep Generative Modeling

Part B: Foundations and Perspectives of Diffusion Models

Part C: Sampling of Diffusion Models

Part D: Toward Learning Fast Diffusion-Based Generators

Epilogue & Outlook

Appendices