Search Results for author: Stephan Eckstein

Found 9 papers, 2 papers with code

Optimal nonparametric estimation of the expected shortfall risk

no code implementations1 May 2024 Daniel Bartl, Stephan Eckstein

We address the problem of estimating the expected shortfall risk of a financial loss using a finite number of i. i. d.

Hilbert's projective metric for functions of bounded growth and exponential convergence of Sinkhorn's algorithm

no code implementations7 Nov 2023 Stephan Eckstein

Motivated by the entropic optimal transport problem in unbounded settings, we study versions of Hilbert's projective metric for spaces of integrable functions of bounded growth.

Convergence Rates for Regularized Optimal Transport via Quantization

no code implementations30 Aug 2022 Stephan Eckstein, Marcel Nutz

We study the convergence of divergence-regularized optimal transport as the regularization parameter vanishes.

Quantization

MinMax Methods for Optimal Transport and Beyond: Regularization, Approximation and Numerics

2 code implementations NeurIPS 2020 Luca De Gennaro Aquino, Stephan Eckstein

We study MinMax solution methods for a general class of optimization problems related to (and including) optimal transport.

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

no code implementations29 Sep 2020 Stephan Eckstein

This note shows that, for a fixed Lipschitz constant $L > 0$, one layer neural networks that are $L$-Lipschitz are dense in the set of all $L$-Lipschitz functions with respect to the uniform norm on bounded sets.

Martingale transport with homogeneous stock movements

no code implementations27 Aug 2019 Stephan Eckstein, Michael Kupper

We study a variant of the martingale optimal transport problem in a multi-period setting to derive robust price bounds of a financial derivative.

Robust risk aggregation with neural networks

no code implementations1 Nov 2018 Stephan Eckstein, Michael Kupper, Mathias Pohl

We work with the set of distributions that are both close to the given reference measure in a transportation distance (e. g. the Wasserstein distance), and additionally have the correct marginal structure.

Computation of optimal transport and related hedging problems via penalization and neural networks

1 code implementation23 Feb 2018 Stephan Eckstein, Michael Kupper

This paper presents a widely applicable approach to solving (multi-marginal, martingale) optimal transport and related problems via neural networks.

Portfolio Optimization

Cannot find the paper you are looking for? You can Submit a new open access paper.