20–22 May 2026
A-8010 Graz
Europe/Vienna timezone

Preconditioned Langevin sampling for Bayesian imaging

21 May 2026, 11:45
25m
HS BMT (BMTEG138), Stremayrgasse 16

HS BMT (BMTEG138), Stremayrgasse 16

TU Graz / Campus Neue Technik 8010 Graz

Speaker

Dr Andreas Habring

Description

In this talk we consider time- and space-dependent preconditioning for Langevin sampling from posteriors arising in Bayesian inverse imaging problems, in particular, MRI. Inspired by quasi-Newton methods in optimization, we consider learned preconditioners which use curvature information to accelerate sampling. We provide a careful theoretical analysis of the sampling methods based on the discretization of the corresponding time-inhomogeneous preconditioned Langevin diffusion as well as experimental results for small scale problems and Bayesian imaging.

Author

Co-authors

Presentation materials

There are no materials yet.