English

Port--Hamiltonian Diffusion Models: A Control-Theoretic Perspective on Generative Modeling

Mathematical Physics 2026-01-13 v1 math.MP

Abstract

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.

Keywords

Cite

@article{arxiv.2601.06071,
  title  = {Port--Hamiltonian Diffusion Models: A Control-Theoretic Perspective on Generative Modeling},
  author = {Majid Darehmiraki},
  journal= {arXiv preprint arXiv:2601.06071},
  year   = {2026}
}

Comments

17 pages, 3 figure

R2 v1 2026-07-01T08:58:09.569Z