Book contents
- Frontmatter
- Dedication
- Contents
- Preface
- Acknowledgments
- Why Stochastic Thermodynamics of Machine Learning?
- Part I Preliminaries
- Part II Discrete-Time Stochastic Dynamics
- 4 Latent Variable Models and Graphical Models
- 5 Thermodynamics of Probabilistic Machine Learning
- 6 Belief Propagation
- 7 The Variational Autoencoder
- 8 Normalizing Flows
- 9 Markov Processes and Time Reversal
- 10 Stochastic Thermodynamics
- 11 Markov Chain Monte Carlo
- 12 Sequential Importance Sampling
- 13 Variational Diffusion Models
- 14 Schrödinger Bridges
- 15 Optimal Control
- 16 Generative Flow Networks
- 17 Fluctuation Theorems
- 18 Free Energy Estimation
- 19 Escorted Free Energy Estimations and Fluctuation Theorems
- 20 Hybrid Stochastic Flows and Surjective Flows
- Part III Continuous-Time Probabilistic Dynamics
- 21 Stochastic Thermodynamics from the Fokker–Planck Equation
- 22 Optimal Transport and Schrödinger Bridge
- 23 Continuous Normalizing Flows and Flow Matching
- Part IV Epilogue
- Bibliography
- Index
16 - Generative Flow Networks
from Part II - Discrete-Time Stochastic Dynamics
Published online by Cambridge University Press: 20 July 2026
Book contents
- Frontmatter
- Dedication
- Contents
- Preface
- Acknowledgments
- Why Stochastic Thermodynamics of Machine Learning?
- Part I Preliminaries
- Part II Discrete-Time Stochastic Dynamics
- 4 Latent Variable Models and Graphical Models
- 5 Thermodynamics of Probabilistic Machine Learning
- 6 Belief Propagation
- 7 The Variational Autoencoder
- 8 Normalizing Flows
- 9 Markov Processes and Time Reversal
- 10 Stochastic Thermodynamics
- 11 Markov Chain Monte Carlo
- 12 Sequential Importance Sampling
- 13 Variational Diffusion Models
- 14 Schrödinger Bridges
- 15 Optimal Control
- 16 Generative Flow Networks
- 17 Fluctuation Theorems
- 18 Free Energy Estimation
- 19 Escorted Free Energy Estimations and Fluctuation Theorems
- 20 Hybrid Stochastic Flows and Surjective Flows
- Part III Continuous-Time Probabilistic Dynamics
- 21 Stochastic Thermodynamics from the Fokker–Planck Equation
- 22 Optimal Transport and Schrödinger Bridge
- 23 Continuous Normalizing Flows and Flow Matching
- Part IV Epilogue
- Bibliography
- Index
Summary
Throughout most of the book we have been discussing Markov chains, which are graphical models that can be depicted as chain graphs. Diffusion models and sequential importance sampling methods are good examples of this, and they have been very successful. In Chapter 4, we also introduced graphical models that can be depicted as directed acyclic graphs (DAGs), and explained how inference and learning can be executed on them in Chapter 6.
Information
- Type
- Chapter
- Information
- Generative AI and Stochastic ThermodynamicsA Tale of Free Energies, pp. 172 - 177Publisher: Cambridge University PressPrint publication year: 2026
Accessibility standard: Unknown
Why this information is here
This section outlines the accessibility features of this content - including support for screen readers, full keyboard navigation and high-contrast display options. This may not be relevant for you.Accessibility Information
Accessibility compliance for the PDF of this chapter is currently unknown
and may be updated in the future.