Radon--Wasserstein Gradient Flows for Interacting-Particle Sampling in High Dimensions
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910013910417408 |
|---|---|
| author | Hess-Childs, Elias Slepčev, Dejan Xu, Lantian |
| author_facet | Hess-Childs, Elias Slepčev, Dejan Xu, Lantian |
| contents | Gradient flows of the Kullback--Leibler (KL) divergence, such as the Fokker--Planck equation and Stein Variational Gradient Descent, evolve a distribution toward a target density known only up to a normalizing constant. We introduce new gradient flows of the KL divergence with a remarkable combination of properties: they admit accurate interacting-particle approximations in high dimensions, and the per-step cost scales linearly in both the number of particles and the dimension. These gradient flows are based on new transportation-based Riemannian geometries on the space of probability measures: the Radon--Wasserstein geometry and the related Regularized Radon--Wasserstein (RRW) geometry. We define these geometries using the Radon transform so that the gradient-flow velocities depend only on one-dimensional projections. This yields interacting-particle-based algorithms whose per-step cost follows from efficient Fast Fourier Transform-based evaluation of the required 1D convolutions. We additionally provide numerical experiments that study the performance of the proposed algorithms and compare convergence behavior and quantization. Finally, we prove some theoretical results including well-posedness of the flows and long-time convergence guarantees for the RRW flow. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_05227 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Radon--Wasserstein Gradient Flows for Interacting-Particle Sampling in High Dimensions Hess-Childs, Elias Slepčev, Dejan Xu, Lantian Machine Learning Numerical Analysis Analysis of PDEs Methodology 65M75, 35Q62, 35Q68, 35Q70, 62-08, 82C22, 49Q22 Gradient flows of the Kullback--Leibler (KL) divergence, such as the Fokker--Planck equation and Stein Variational Gradient Descent, evolve a distribution toward a target density known only up to a normalizing constant. We introduce new gradient flows of the KL divergence with a remarkable combination of properties: they admit accurate interacting-particle approximations in high dimensions, and the per-step cost scales linearly in both the number of particles and the dimension. These gradient flows are based on new transportation-based Riemannian geometries on the space of probability measures: the Radon--Wasserstein geometry and the related Regularized Radon--Wasserstein (RRW) geometry. We define these geometries using the Radon transform so that the gradient-flow velocities depend only on one-dimensional projections. This yields interacting-particle-based algorithms whose per-step cost follows from efficient Fast Fourier Transform-based evaluation of the required 1D convolutions. We additionally provide numerical experiments that study the performance of the proposed algorithms and compare convergence behavior and quantization. Finally, we prove some theoretical results including well-posedness of the flows and long-time convergence guarantees for the RRW flow. |
| title | Radon--Wasserstein Gradient Flows for Interacting-Particle Sampling in High Dimensions |
| topic | Machine Learning Numerical Analysis Analysis of PDEs Methodology 65M75, 35Q62, 35Q68, 35Q70, 62-08, 82C22, 49Q22 |
| url | https://arxiv.org/abs/2602.05227 |