langevin-dynamics-skill

Layer 5: SDE-Based Learning Analysis via Langevin Dynamics

Version: 1.0.0 Trit: 0 (Ergodic - understands convergence) Bundle: analysis Status: ✅ New (based on Moritz Schauer's approach)

Overview

Langevin Dynamics Skill implements Moritz Schauer's approach to understanding neural network training through stochastic differential equations (SDEs). Instead of treating training as a black-box optimization, this skill instruments the randomness to reveal:

1. Temperature control: How noise scale affects exploration vs exploitation
2. Fokker-Planck convergence: When training reaches equilibrium
3. Mixing time: How long until the network reaches steady state
4. Discretization effects: How learning rate affects continuous theory