31 citations · 113 across the 17 of their papers we have counts for
18 papers
Representations from Pretrained Machine-Learning Interatomic Potentials as Coarse Coordinates for Material Generation and Evaluation
Paul Hagemann, Katharina Ueltzen, Simon Müller +2
Generative machine learning is increasingly used for inorganic crystal structure generation. Most models and the corresponding evaluation approaches rely on simple forms of crystal…
Transport Novelty Distance: A Distributional Metric for Evaluating Material Generative Models
Paul Hagemann, Simon Müller, Janine George +1
Recent advances in generative machine learning have opened new possibilities for the discovery and design of novel materials. However, as these models become more sophisticated, th…
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…
Sampling from Boltzmann densities with physics informed low-rank formats
Paul Hagemann, Janina Schütte, David Sommer +2
Our method proposes the efficient generation of samples from an unnormalized Boltzmann density by solving the underlying continuity equation in the low-rank tensor train (TT) forma…
PnP-Flow: Plug-and-Play Image Restoration with Flow Matching
Ségolène Martin, Anne Gagneux, Paul Hagemann +1
In this paper, we introduce Plug-and-Play (PnP) Flow Matching, an algorithm for solving imaging inverse problems. PnP methods leverage the strength of pre-trained denoisers, often…
Conditional Wasserstein Distances with Applications in Bayesian OT Flow Matching
Jannis Chemseddine, Paul Hagemann, Gabriele Steidl +1
In inverse problems, many conditional generative models approximate the posterior measure by minimizing a distance between the joint measure and its learned approximation. While th…
Mixed Noise and Posterior Estimation with Conditional DeepGEM
Paul Hagemann, Johannes Hertrich, Maren Casfor +2
Motivated by indirect measurements and applications from nanometrology with a mixed noise model, we develop a novel algorithm for jointly estimating the posterior and the noise par…
Learning from small data sets: Patch-based regularizers in inverse problems for image reconstruction
Moritz Piening, Fabian Altekrüger, Johannes Hertrich +3
The solution of inverse problems is of fundamental interest in medical and astronomical imaging, geophysics as well as engineering and life sciences. Recent advances were made by u…
Y-Diagonal Couplings: Approximating Posteriors with Conditional Wasserstein Distances
Jannis Chemseddine, Paul Hagemann, Christian Wald
In inverse problems, many conditional generative models approximate the posterior measure by minimizing a distance between the joint measure and its learned approximation. While th…
Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel
Paul Hagemann, Johannes Hertrich, Fabian Altekrüger +3
We propose conditional flows of the maximum mean discrepancy (MMD) with the negative distance kernel for posterior sampling and conditional generative modeling. This MMD, which is…
Generative Sliced MMD Flows with Riesz Kernels
Johannes Hertrich, Christian Wald, Fabian Altekrüger +1
Maximum mean discrepancy (MMD) flows suffer from high computational costs in large scale computations. In this paper, we show that MMD flows with Riesz kernels $K(x,y) = - \|x-y\|^…
Conditional Generative Models are Provably Robust: Pointwise Guarantees for Bayesian Inverse Problems
Fabian Altekrüger, Paul Hagemann, Gabriele Steidl
Conditional generative models became a very powerful tool to sample from Bayesian inverse problem posteriors. It is well-known in classical Bayesian literature that posterior measu…
Multilevel Diffusion: Infinite Dimensional Score-Based Diffusion Models for Image Generation
Paul Hagemann, Sophie Mildenberger, Lars Ruthotto +2
Score-based diffusion models (SBDM) have recently emerged as state-of-the-art approaches for image generation. Existing SBDMs are typically formulated in a finite-dimensional setti…
PatchNR: Learning from Very Few Images by Patch Normalizing Flow Regularization
Fabian Altekrüger, Alexander Denker, Paul Hagemann +3
Learning neural networks using only few available information is an important ongoing research topic with tremendous potential for applications. In this paper, we introduce a power…
Generalized Normalizing Flows via Markov Chains
Paul Hagemann, Johannes Hertrich, Gabriele Steidl
Normalizing flows, diffusion normalizing flows and variational autoencoders are powerful generative models. This chapter provides a unified framework to handle these approaches via…
Stochastic Normalizing Flows for Inverse Problems: a Markov Chains Viewpoint
Paul Hagemann, Johannes Hertrich, Gabriele Steidl
To overcome topological constraints and improve the expressiveness of normalizing flow architectures, Wu, Köhler and Noé introduced stochastic normalizing flows which combine deter…
Invertible Neural Networks versus MCMC for Posterior Reconstruction in Grazing Incidence X-Ray Fluorescence
Anna Andrle, Nando Farchmin, Paul Hagemann +3
Grazing incidence X-ray fluorescence is a non-destructive technique for analyzing the geometry and compositional parameters of nanostructures appearing e.g. in computer chips. In t…
Stabilizing Invertible Neural Networks Using Mixture Models
Paul Hagemann, Sebastian Neumayer
In this paper, we analyze the properties of invertible neural networks, which provide a way of solving inverse problems. Our main focus lies on investigating and controlling the Li…