3 papers
cs.LG2025
Provable Mixed-Noise Learning with Flow-Matching
Paul Hagemann, Robert Gruhlke, Bernhard Stankewitz +2
We study Bayesian inverse problems with mixed noise, modeled as a combination of additive and multiplicative Gaussian components. While traditional inference methods often assume f…
stat.ML2025
Gradient-Free Sequential Bayesian Experimental Design via Interacting Particle Systems
Robert Gruhlke, Matei Hanu, Claudia Schillings +1
We introduce a gradient-free framework for Bayesian Optimal Experimental Design (BOED) in sequential settings, aimed at complex systems where gradient information is unavailable. O…
math.NA2020
Low-rank tensor reconstruction of concentrated densities with application to Bayesian inversion
Martin Eigel, Robert Gruhlke, Manuel Marschall
Transport maps have become a popular mechanic to express complicated probability densities using sample propagation through an optimized push-forward. Beside their broad applicabil…