6 papers
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…
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…
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…
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…
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…
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…