Generative thermodynamic computing

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autor principal: Whitelam, Stephen
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911240981315584
author Whitelam, Stephen
author_facet Whitelam, Stephen
contents We introduce a generative modeling framework for thermodynamic computing, in which structured data is synthesized from noise by the natural time evolution of a physical system governed by Langevin dynamics. While conventional diffusion models use neural networks to perform denoising, here the information needed to generate structure from noise is encoded by the dynamics of a thermodynamic system. Training proceeds by maximizing the probability with which the computer generates the reverse of a noising trajectory, which ensures that the computer generates data with minimal heat emission. We demonstrate this framework within a digital simulation of a thermodynamic computer. If realized in analog hardware, such a system would function as a generative model that produces structured samples without the need for artificially-injected noise or active control of denoising.
format Preprint
id arxiv_https___arxiv_org_abs_2506_15121
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generative thermodynamic computing
Whitelam, Stephen
Statistical Mechanics
Neural and Evolutionary Computing
We introduce a generative modeling framework for thermodynamic computing, in which structured data is synthesized from noise by the natural time evolution of a physical system governed by Langevin dynamics. While conventional diffusion models use neural networks to perform denoising, here the information needed to generate structure from noise is encoded by the dynamics of a thermodynamic system. Training proceeds by maximizing the probability with which the computer generates the reverse of a noising trajectory, which ensures that the computer generates data with minimal heat emission. We demonstrate this framework within a digital simulation of a thermodynamic computer. If realized in analog hardware, such a system would function as a generative model that produces structured samples without the need for artificially-injected noise or active control of denoising.
title Generative thermodynamic computing
topic Statistical Mechanics
Neural and Evolutionary Computing
url https://arxiv.org/abs/2506.15121