Preconditioned Regularized Wasserstein Proximal Sampling

Abstract. We consider sampling from a Gibbs distribution by evolving finitely many particles. We propose a preconditioned version of a recently proposed noise-free sampling method, governed by approximating the score function with the numerically tractable score of a regularized Wasserstein proximal operator. This is derived by a Cole–Hopf transformation on coupled anisotropic heat equations, yielding a kernel formulation for the preconditioned regularized Wasserstein proximal. The diffusion component of the proposed method is also interpreted as a modified self-attention block, as in transformer architectures. For quadratic potentials, we provide a discrete-time nonasymptotic convergence analysis and explicitly characterize the bias, which is dependent on regularization and independent of step-size. Experiments demonstrate acceleration and particle-level stability on various log-concave and non-log-concave toy examples, as well as for Bayesian total-variation regularized image deconvolution. We further show competitive/better performance on nonconvex Bayesian neural network training when utilizing variable preconditioning matrices.

Authors

Institutions

Publication Details

Journal
SIAM/ASA Journal on Uncertainty Quantification
Published
2026-11-16
DOI
https://doi.org/10.1137/25m1794097
Citations
2
Primary Topic
Markov Chains and Monte Carlo Methods
Type
article
Field-Weighted Citation Impact
2.92

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Preconditioned Regularized Wasserstein Proximal Sampling

Stanley Osher, Wuchen Li, Hong Ye Tan
2 citations
SIAM/ASA Journal on Uncertainty Quantification
Markov Chains and Monte Carlo Methods
2.92
article

Preconditioned Regularized Wasserstein Proximal Sampling

Stanley Osher, Wuchen Li, Hong Ye Tan
article en
2 citations

Abstract

Abstract. We consider sampling from a Gibbs distribution by evolving finitely many particles. We propose a preconditioned version of a recently proposed noise-free sampling method, governed by approximating the score function with the numerically tractable score of a regularized Wasserstein proximal operator. This is derived by a Cole–Hopf transformation on coupled anisotropic heat equations, yielding a kernel formulation for the preconditioned regularized Wasserstein proximal. The diffusion component of the proposed method is also interpreted as a modified self-attention block, as in transformer architectures. For quadratic potentials, we provide a discrete-time nonasymptotic convergence analysis and explicitly characterize the bias, which is dependent on regularization and independent of step-size. Experiments demonstrate acceleration and particle-level stability on various log-concave and non-log-concave toy examples, as well as for Bayesian total-variation regularized image deconvolution. We further show competitive/better performance on nonconvex Bayesian neural network training when utilizing variable preconditioning matrices.

SIAM/ASA Journal on Uncertainty QuantificationVol. 14(4)
University of South Carolina (US), University of California, Los Angeles (US)
National Science Foundation, Masason Foundation, Division of Mathematical Sciences, Air Force Office of Scientific Research
Openalex Percentile: Top 12%
Markov Chains and Monte Carlo Methods
2.92
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon