Mathematics for AI and Machine Learning

Foundations for modern AI and machine learning

Detailed Balance

Chapter 21 Dynamics & diffusion

Chapter 21: Fokker-Planck and Distribution Dynamics — Stationary Distributions and Detailed Balance

Animated preview (GIF)
Detailed Balance — animated GIF preview
High-resolution PNG
Detailed Balance — high-resolution mind-map icon

From the book

Chapter 21: Fokker-Planck and Distribution Dynamics. In the chapter mind map this icon labels Stationary Distributions and Detailed Balance. The discussion below is excerpted and lightly edited from § Stationary Distributions and Detailed Balance in Mathematics for AI and Machine Learning.

At equilibrium (stationary state), $\partial_t p_t = 0$, yielding:

whose solution is exactly $p(\mathbf{x})$, the target distribution.

  • Left side: $\nabla^2 p$
  • Right side: $\nabla \cdot (p \nabla \log p) = \nabla \cdot \nabla p = \nabla^2 p$

So the equation is satisfied, confirming that $p$ is indeed a stationary solution.

What this drawing shows

What you see. Stationary weights $p^*$ fixed; paired forward and reverse flux arrows grow symmetrically, illustrating detailed balance at equilibrium.

In the mind map. Chapter 21 — Stationary Distributions and Detailed Balance. See From the book above for definitions, figures, and worked examples.

Where to read next

Open Chapter 21 companion →

Read the full definitions, figures, and worked examples in Chapter 21: Fokker-Planck and Distribution Dynamics — see the mind-map node Stationary Distributions and Detailed Balance.