Work

Diffusion reconstruction for the diluted Ising model

Year: 2025

Type: article

Abstract: Diffusion-based generative models are machine learning models that use diffusion processes to learn the probability distribution of high-dimensional data. In recent years they have become extremely successful in generating multimedia content. However, it is still unknown whether such models can be used to generate high-quality datasets of physical models. In this work we use a Landau-Ginzburg-like diffusion model to infer the distribution of a two-dimensional bond-diluted Ising model. Our approach is simple and effective, and we show that the generated samples correctly reproduce the statistical and critical properties of the physical model.

Source: Physical review. E

DOI: 10.1103/physreve.111.l023301

Authors: Stefano Bae, Enzo Marinari, Federico Ricci-Tersenghi

Institutions: Sapienza University of Rome, Istituto Nazionale di Fisica Nucleare, Sezione di Roma I

Language: English

Topic: Theoretical and Computational Physics

Subfield: Condensed Matter Physics

Field: Physics and Astronomy

Domain: Physical Sciences

Open Access status: green