1 citations · 3 across the 18 of their papers we have counts for
10 papers · 1 filter
Self-Aware Markov Models for Discrete Reasoning
Gregor Kornhardt, Jannis Chemseddine, Christian Wald +1
Standard masked discrete diffusion models face limitations in reasoning tasks due to their inability to correct their own mistakes on the masking path. Since they rely on a fixed n…
SympFormer: Accelerated attention blocks via Inertial Dynamics on Density Manifolds
Viktor Stein, Wuchen Li, Gabriele Steidl
Transformers owe much of their empirical success in natural language processing to the self-attention blocks. Recent perspectives interpret attention blocks as interacting particle…
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…
Variable Bregman Majorization-Minimization Algorithm and its Application to Dirichlet Maximum Likelihood Estimation
Ségolène Martin, Jean-Christophe Pesquet, Gabriele Steidl +1
We propose a novel Bregman descent algorithm for minimizing a convex function that is expressed as the sum of a differentiable part (defined over an open set) and a possibly nonsmo…
Joint Metric Space Embedding by Unbalanced OT with Gromov-Wasserstein Marginal Penalization
Florian Beier, Moritz Piening, Robert Beinert +1
We propose a new approach for unsupervised alignment of heterogeneous datasets, which maps data from two different domains without any known correspondences to a common metric spac…
Flow Matching: Markov Kernels, Stochastic Processes and Transport Plans
Christian Wald, Gabriele Steidl
Among generative neural models, flow matching techniques stand out for their simple applicability and good scaling properties. Here, velocity fields of curves connecting a simple l…
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…
Neural Sampling from Boltzmann Densities: Fisher-Rao Curves in the Wasserstein Geometry
Jannis Chemseddine, Christian Wald, Richard Duong +1
We deal with the task of sampling from an unnormalized Boltzmann density by learning a Boltzmann curve given by energies starting in a simple density . First, we e…
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…