Viktor Stein

Applied mathematician working on Wasserstein gradient flows, regularized divergences, optimal transport, and geometry-inspired machine learning.

  • J. Bresch, V. Stein: Interpolating between Optimal Transport and KL regularized Optimal Transport using Rényi Divergences. Results in Mathematics 81, 23 (2026). arXiv · Journal · Code · Slides

  • R. Duong, V. Stein, R. Beinert, J. Hertrich, G. Steidl: Wasserstein Gradient Flows of MMD Functionals with Distance Kernel and Cauchy Problems on Quantile Functions. ESAIM: Control, Optimisation and Calculus of Variations. Abstract · PDF · Code

  • V. Stein, S. Neumayer, N. Rux, G. Steidl: Wasserstein Gradient Flows for Moreau Envelopes of f-Divergences in Reproducing Kernel Hilbert Spaces. Analysis and Applications 24(1), 21–65 (2026). Journal version · arXiv · Code

  • R. Duong, N. Rux, V. Stein, G. Steidl: Wasserstein Gradient Flows of MMD Functionals with Distance Kernels under Sobolev Regularization. Philosophical Transactions of the Royal Society A, special issue “Partial Differential Equations in Data Science”. Abstract · PDF · Journal version

  • V. Stein, Wuchen Li: Accelerated Stein Variational Gradient Flow. In: Proceedings of GSI’25: Geometric Science of Information (LNCS 16034). arXiv · Code · Slides · Video · Published version

Preprints

  • SympFormer: Accelerated attention blocks via Inertial Dynamics on Density Manifolds
    joint work with Wuchen Li and Gabriele Steidl
    PDF · Code

  • Well-Posed KL-Regularized Control via Wasserstein and Kalman-Wasserstein KL Divergences
    joint work with Adwait Datar and Nihat Ay, submitted to ICML’26
    PDF

  • Approximating f-Divergences with Rank Statistics
    joint work with José Manuel de Frutos, submitted to ICML’26
    PDF · Code

  • Towards understanding Accelerated Stein Variational Gradient Flow – Analysis of Generalized Bilinear Kernels for Gaussian target distributions
    joint work with Wuchen Li, submitted to JMLR
    PDF · Code