Salvato in:
Dettagli Bibliografici
Autore principale: Darehmiraki, Majid
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2601.06071
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911365566824448
author Darehmiraki, Majid
author_facet Darehmiraki, Majid
contents Diffusion models have recently achieved remarkable success in generative modeling, yet they are commonly formulated as black-box stochastic systems with limited interpretability and few structural guarantees. In this paper, we establish a control-theoretic foundation for diffusion models by embedding them within the port--Hamiltonian (PH) systems framework. We show that the score function can be interpreted as the gradient of a learnable Hamiltonian energy, allowing both the forward and reverse diffusion processes to be formulated as structured PH dynamics. The reverse-time generative process is further interpreted as a feedback-controlled PH system, where dissipation plays a fundamental role in stabilizing sampling dynamics. This formulation yields intrinsic stability guarantees that are independent of score estimation accuracy. A simple analytical example illustrates the proposed framework.
format Preprint
id arxiv_https___arxiv_org_abs_2601_06071
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Port--Hamiltonian Diffusion Models: A Control-Theoretic Perspective on Generative Modeling
Darehmiraki, Majid
Mathematical Physics
60H10, 34H05
Diffusion models have recently achieved remarkable success in generative modeling, yet they are commonly formulated as black-box stochastic systems with limited interpretability and few structural guarantees. In this paper, we establish a control-theoretic foundation for diffusion models by embedding them within the port--Hamiltonian (PH) systems framework. We show that the score function can be interpreted as the gradient of a learnable Hamiltonian energy, allowing both the forward and reverse diffusion processes to be formulated as structured PH dynamics. The reverse-time generative process is further interpreted as a feedback-controlled PH system, where dissipation plays a fundamental role in stabilizing sampling dynamics. This formulation yields intrinsic stability guarantees that are independent of score estimation accuracy. A simple analytical example illustrates the proposed framework.
title Port--Hamiltonian Diffusion Models: A Control-Theoretic Perspective on Generative Modeling
topic Mathematical Physics
60H10, 34H05
url https://arxiv.org/abs/2601.06071