Diffusion models learn distributions generated by complex Langevin dynamics

TL;DR

This paper investigates whether diffusion models, a type of generative AI, can learn and replicate the complex probability distributions produced by complex Langevin dynamics, which are difficult to understand and sample.

Contribution

It demonstrates the potential of diffusion models to learn distributions generated by complex Langevin processes, addressing a key challenge in understanding these complex systems.

Findings

Diffusion models successfully learn complex Langevin distributions

The approach offers new insights into sign problem theories

Potential applications in quantum field theories with sign problems

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.