Diffusion models learn distributions generated by complex Langevin dynamics

Diaa E. Habibi, Gert Aarts, Lingxiao Wang, Kai Zhou
12/2/2024
hep-latcs.LG

No confident code implementation found for this paper.

Abstract

The probability distribution effectively sampled by a complex Langevin process for theories with a sign problem is not known a priori and notoriously hard to understand. Diffusion models, a class of generative AI, can learn distributions from data. In this contribution, we explore the ability of diffusion models to learn the distributions created by a complex Langevin process.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Combining complex Langevin dynamics with score-based and energy-based diffusion models

95% match2025

Nonequilbrium physics of generative diffusion models

83% match2024

Non-asymptotic Analysis of Diffusion Annealed Langevin Monte Carlo for Generative Modelling

83% match2025

Generative Diffusion Models for Lattice Field Theory

83% match2023

Diffusion Models are Molecular Dynamics Simulators

83% match2025

A theory of learning data statistics in diffusion models, from easy to hard

82% match2026

Cite this paper

@article{habibi2024diffusion,
  title  = {Diffusion models learn distributions generated by complex Langevin dynamics},
  author = {Diaa E. Habibi and Gert Aarts and Lingxiao Wang and Kai Zhou},
  year   = {2024},
  eprint = {2412.01919},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2412.01919v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2412.01919.svg)](https://codeofpaper.com/paper/2412.01919)

Discussion