Generative AI and Stochastic Thermodynamics

A Tale of Free Energies

AvMax Welling,Sirui Lu

Häftad, Engelska, 2026

355 kr

Kommande

Fler format och utgåvor

Inbunden

Kommande

Beskrivning

Originating from lectures delivered at the African Institute of Mathematical Sciences, this book presents a unifying perspective on traditional and modern methods in generative AI and stochastic thermodynamics. By relating the core topics in machine learning to the notion of (variational) free-energy, a bridge is built between methods such as latent variable models, variational auto-encoders, optimal control, optimal transport, normalizing flows and diffusion models and concepts such as entropy production and fluctuation theorems in stochastic thermodynamics. Structured into three main parts, the book commences by setting up the required mathematical and statistical physics preliminaries needed to make it broadly accessible. The largest part of the book then focuses on building intuition of major advances in generative AI by considering discrete time processes and their relationship to topics in stochastic thermodynamics. Finally, the authors take a short excursion to the continuous time domain for the more advanced learner.

Produktinformation

Utgivningsdatum:2026-07-31
Format:Häftad
Språk:Engelska
Antal sidor:307
Förlag:Cambridge University Press
ISBN:9781009709033

Utforska kategorier

Fysik inom Naturvetenskap och teknik
Matematisk fysik inom Naturvetenskap och teknik
Artificiell intelligens inom Data och IT

Mer om författaren

Max Welling is Full Professor in Machine Learning at the University of Amsterdam. He is co-founder and CTO of the startup CuspAI. Professor Welling is a member of the Dutch Royal Academy of Sciences and was the recipient of the ECCV Koenderink Prize in 2010 and the ICML Test of Time award in 2021. Sirui Lu is Doctoral Researcher at the Max Planck Institute of Quantum Optics, Germany. His research directions are the deep integration between (quantum) physics and artificial intelligence. Previously, he obtained his bachelor's degree from the Department of Physics at Tsinghua University, Beijing. Lars Holdijk is Ph.D. student at the University of Oxford. His research focusses on the intersection of Generative Artificial Intelligence, Computational Biochemistry and Statistical Physics.

Innehållsförteckning

Preface; Acknowledgement; Why stochastic thermodynamics of machine learning?; Part I. Preliminaries: 1. Mathematical preliminaries; 2. Neural network preliminaries; 3. Physics 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. Schro¨ dinger 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 Schro¨ dinger bridge; 23. Continuous normalizing flows and flow matching; Part IV. Epilogue: 24. Uniﬁcation: free energy is all you need; Bibliography; Index.

Mer från samma författare

Structured Representation Learning

Yue Song, Thomas Anderson Keller, Nicu Sebe, Max Welling

Inbunden, 2025

489 kr

Del 9905