Radon--Wasserstein Gradient Flows for Interacting-Particle Sampling in High Dimensions

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.

💡 Research Summary

This paper introduces a novel family of gradient flows for sampling high‑dimensional probability distributions, built upon a transportation‑based Riemannian geometry defined via the Radon transform. The authors call the resulting metric the Radon‑Wasserstein (RW) geometry and its regularized variant the Regularized Radon‑Wasserstein (RRW) geometry. By projecting a d‑dimensional density onto one‑dimensional lines (parameterized by directions θ∈S^{d‑1}) and working with the resulting Radon densities Rθρ, the authors obtain a gradient‑flow velocity field that depends only on one‑dimensional quantities: \