langevin-dynamics
OfficialBridge theory to practice in SDE learning.
Authorplurigrid
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Langevin dynamics are used to study neural network learning by injecting controlled noise to analyze exploration, convergence, and discretization effects in training dynamics.
Core Features & Use Cases
- Solve Langevin SDEs: compare multiple discretization solvers.
- Fokker-Planck convergence: empirically verify proximity to Gibbs distribution.
- Mixing time estimation: evaluate when training equilibrates.
- Temperature effects: study how noise level influences exploration vs exploitation.
- Discretization study: observe how different dt alter results.
Quick Start
just langevin-solve net=logistic T=0.01 dt=0.01
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: langevin-dynamics Download link: https://github.com/plurigrid/asi/archive/main.zip#langevin-dynamics Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.