activity
20242026
collaborators

6 papers

stat.ML2026

Tensor Train Diffusion: Leveraging Low-Rank Structures for High-Dimensional Score-Based Sampling

Robert Gruhlke, Julius Berner, David Sommer +1

Diffusion models offer a powerful framework for sampling from complex probability densities by learning to reverse a noising process. A common approach involves solving for the tim…

math.OC2026

Optimal sampling for stochastic and natural gradient descent

Robert Gruhlke, Anthony Nouy, Philipp Trunschke

We consider the problem of optimising the expected value of a loss functional over a nonlinear model class of functions, assuming that we have only access to realisations of the gr…

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…

stat.ML2025

Importance Corrected Neural JKO Sampling

Johannes Hertrich, Robert Gruhlke

In order to sample from an unnormalized probability density function, we propose to combine continuous normalizing flows (CNFs) with rejection-resampling steps based on importance…

math.NA2024

Generative modeling with low-rank Wasserstein polynomial chaos expansions

Robert Gruhlke, Martin Eigel

A new Wasserstein multi-element polynomial chaos expansion (WPCE) is proposed, which is inspired by recent advances in computational optimal transport for estimating Wasserstein di…