HOTA: Hamiltonian framework for Optimal Transport Advection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Buzun, Nazar, Shlenskii, Daniil, Bobrin, Maxim, Dylov, Dmitry V.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911164737257472
author Buzun, Nazar
Shlenskii, Daniil
Bobrin, Maxim
Dylov, Dmitry V.
author_facet Buzun, Nazar
Shlenskii, Daniil
Bobrin, Maxim
Dylov, Dmitry V.
contents Optimal transport (OT) has become a natural framework for guiding the probability flows. Yet, the majority of recent generative models assume trivial geometry (e.g., Euclidean) and rely on strong density-estimation assumptions, yielding trajectories that do not respect the true principles of optimality in the underlying manifold. We present Hamiltonian Optimal Transport Advection (HOTA), a Hamilton-Jacobi-Bellman based method that tackles the dual dynamical OT problem explicitly through Kantorovich potentials, enabling efficient and scalable trajectory optimization. Our approach effectively evades the need for explicit density modeling, performing even when the cost functionals are non-smooth. Empirically, HOTA outperforms all baselines in standard benchmarks, as well as in custom datasets with non-differentiable costs, both in terms of feasibility and optimality.
format Preprint
id arxiv_https___arxiv_org_abs_2507_17513
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HOTA: Hamiltonian framework for Optimal Transport Advection
Buzun, Nazar
Shlenskii, Daniil
Bobrin, Maxim
Dylov, Dmitry V.
Machine Learning
Artificial Intelligence
Optimal transport (OT) has become a natural framework for guiding the probability flows. Yet, the majority of recent generative models assume trivial geometry (e.g., Euclidean) and rely on strong density-estimation assumptions, yielding trajectories that do not respect the true principles of optimality in the underlying manifold. We present Hamiltonian Optimal Transport Advection (HOTA), a Hamilton-Jacobi-Bellman based method that tackles the dual dynamical OT problem explicitly through Kantorovich potentials, enabling efficient and scalable trajectory optimization. Our approach effectively evades the need for explicit density modeling, performing even when the cost functionals are non-smooth. Empirically, HOTA outperforms all baselines in standard benchmarks, as well as in custom datasets with non-differentiable costs, both in terms of feasibility and optimality.
title HOTA: Hamiltonian framework for Optimal Transport Advection
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2507.17513