Efficient Learning of Stationary Diffusions With Stein-Type Discrepancies

MCML Authors

Fabian Bleile

→ Group Mathias Drton
 Mathematical Statistics

Mathias Drton

Prof. Dr.

Core PI

Mathematical Statistics

Abstract

Learning a stationary diffusion amounts to estimating the parameters of a stochastic differential equation whose stationary distribution matches a target distribution. We build on the recently introduced kernel deviation from stationarity (KDS), which enforces stationarity by evaluating expectations of the diffusion's generator in a reproducing kernel Hilbert space. Leveraging the connection between KDS and Stein discrepancies, we introduce the Stein-type KDS (SKDS) as an alternative formulation. We prove that a vanishing SKDS guarantees alignment of the learned diffusion's stationary distribution with the target. Furthermore, under broad parametrizations, SKDS is convex with an empirical version that is ϵ-quasiconvex with high probability. Empirically, learning with SKDS attains comparable accuracy to KDS while substantially reducing computational cost and yields improvements over the majority of competitive baselines.

inproceedings BLD26

---

AISTATS 2026

29th International Conference on Artificial Intelligence and Statistics. Tangier, Morocco, May 02-05, 2026. To be published. Preprint available.

---

Authors

F. Bleile • S. Lumpp • M. Drton

---

Links

arXiv

---

Research Area

 A1 | Statistical Foundations & Explainability