Paper Detail

Data Free Training of Diffusion Models for Lattice Field Theories

Dennis Grinwald, Ankur Singha, Khaled Kahouli, Karl Jansen, Shinichi Nakajima

arxiv Score 6.8

Published 2026-10-13 · First seen 2026-10-14

General AI

Abstract

Sampling equilibrium field configurations remains a major computational bottleneck in lattice field theory, motivating the development of generative samplers that can produce independent configurations. Diffusion models are promising for this purpose, but their standard denoising score matching objective requires samples from the target distribution, seemingly reintroducing the original sampling problem. Here, we show that diffusion models can instead be trained from their own generated samples using the target score identity, provided access to the unnormalized probability density. Importance-weighted formulations of this identity yield a consistent target throughout training, while unweighted variants define a self-consistent fixed-point training scheme. We benchmark the different approaches in two-dimensional \(φ^4\) theory and identify effective choices that enable efficient training and sampling across the symmetric, critical, and broken phases. Ultimately, our data-free training approach achieves comparable performance to training on HMC reference data.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{grinwald2026data,
  title = {Data Free Training of Diffusion Models for Lattice Field Theories},
  author = {Dennis Grinwald and Ankur Singha and Khaled Kahouli and Karl Jansen and Shinichi Nakajima},
  year = {2026},
  abstract = {Sampling equilibrium field configurations remains a major computational bottleneck in lattice field theory, motivating the development of generative samplers that can produce independent configurations. Diffusion models are promising for this purpose, but their standard denoising score matching objective requires samples from the target distribution, seemingly reintroducing the original sampling problem. Here, we show that diffusion models can instead be trained from their own generated samples },
  url = {https://arxiv.org/abs/2610.18863},
  keywords = {hep-lat, cs.LG},
  eprint = {2610.18863},
  archiveprefix = {arXiv},
}

Metadata

{}