12 citations · 35 across the 14 of their papers we have counts for
6 papers · 1 filter
Gromov-Wasserstein Quantization and Clustering: Structure, Rates, and Algorithms
Florian Beier, Stephan Eckstein
Clustering is a fundamental class of data analysis techniques with the most important representatives being centroid-based methods like -means. Such methods are strongly connect…
Stability and Sample Complexity of Divergence Regularized Optimal Transport
Erhan Bayraktar, Stephan Eckstein, Xin Zhang
We study stability and sample complexity properties of divergence regularized optimal transport (DOT). First, we obtain quantitative stability results for optimizers of DOT measure…
Convergence Rates for Regularized Optimal Transport via Quantization
Stephan Eckstein, Marcel Nutz
We study the convergence of divergence-regularized optimal transport as the regularization parameter vanishes. Sharp rates for general divergences including relative entropy or $L^…
Quantitative Stability of Regularized Optimal Transport and Convergence of Sinkhorn's Algorithm
Stephan Eckstein, Marcel Nutz
We study the stability of entropically regularized optimal transport with respect to the marginals. Lipschitz continuity of the value and Hölder continuity of the optimal coupling…
MinMax Methods for Optimal Transport and Beyond: Regularization, Approximation and Numerics
Luca De Gennaro Aquino, Stephan Eckstein
We study MinMax solution methods for a general class of optimization problems related to (and including) optimal transport. Theoretically, the focus is on fitting a large class of…
Computation of optimal transport and related hedging problems via penalization and neural networks
Stephan Eckstein, Michael Kupper
This paper presents a widely applicable approach to solving (multi-marginal, martingale) optimal transport and related problems via neural networks. The core idea is to penalize th…