Viktor Stein

collaborators

Showing math.APShow all

2 papers · 1 filter

math.AP2024

Wasserstein Gradient Flows of MMD Functionals with Distance Kernels under Sobolev Regularization

Richard Duong, Nicolaj Rux, Viktor Stein +1

We consider Wasserstein gradient flows of maximum mean discrepancy (MMD) functionals $MMD_{K}^{2} (\cdot, ν)$ for positive and negative distance kernels $K (x, y) := \pm ∣ x - y ∣$ and…

math.AP2024

Wasserstein Gradient Flows of MMD Functionals with Distance Kernel and Cauchy Problems on Quantile Functions

Richard Duong, Viktor Stein, Robert Beinert +2

We give a comprehensive description of Wasserstein gradient flows of maximum mean discrepancy (MMD) functionals $F_{ν} := MMD_{K}^{2} (\cdot, ν)$ towards given target measu…