We propose conditional flows of the maximum mean discrepancy (MMD) with the negative
distance kernel for posterior sampling and conditional generative modeling. This MMD …

Wasserstein gradient flows of maximum mean discrepancy (MMD) functionals with non-
smooth Riesz kernels show a rich structure as singular measures can become absolutely …

Sliced optimal transport, which is basically a Radon transform followed by one-dimensional
optimal transport, became popular in various applications due to its efficient computation. In …

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

Most commonly used $ f $-divergences of measures, eg, the Kullback-Leibler divergence,
are subject to limitations regarding the support of the involved measures. A remedy consists …

The aim of this paper is twofold. Based on the geometric Wasserstein tangent space, we first
introduce Wasserstein steepest descent flows. These are locally absolutely continuous …

Kernel-based methods are heavily used in machine learning. However, they suffer from
complexity in the number of considered data points. In this paper, we propose an …

Generative models are invaluable in many fields of science because of their ability to
capture high-dimensional and complicated distributions, such as photo-realistic images …

We give a comprehensive description of Wasserstein gradient flows of maximum mean
discrepancy (MMD) functionals $\mathcal F_\nu:=\text {MMD} _K^ 2 (\cdot,\nu) $ towards …

Generative models are invaluable in many fields of science because of their ability to
capture high-dimensional and complicated distributions, such as photo-realistic images …