activity
20182020
most citedLipschitz neural networks are dense in the set of all Lipschitz functions

2 citations · 2 across the 1 of their papers we have counts for

collaborators

5 papers

math.OC2020

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…

stat.ML20202 cited

Lipschitz neural networks are dense in the set of all Lipschitz functions

Stephan Eckstein

This note shows that, for a fixed Lipschitz constant , one layer neural networks that are -Lipschitz are dense in the set of all -Lipschitz functions with respect to t…

math.PR2019

Robust pricing and hedging of options on multiple assets and its numerics

Stephan Eckstein, Gaoyue Guo, Tongseok Lim +1

We consider robust pricing and hedging for options written on multiple assets given market option prices for the individual assets. The resulting problem is called the multi-margin…

q-fin.MF2018

Robust risk aggregation with neural networks

Stephan Eckstein, Michael Kupper, Mathias Pohl

We consider settings in which the distribution of a multivariate random variable is partly ambiguous. We assume the ambiguity lies on the level of the dependence structure, and tha…

math.OC2018

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…