Computation of optimal transport and related hedging problems via penalization and neural networks
From MaRDI portal
Publication:2020305
DOI10.1007/S00245-019-09558-1zbMATH Open1462.49073arXiv1802.08539OpenAlexW3124391905WikidataQ128353357 ScholiaQ128353357MaRDI QIDQ2020305FDOQ2020305
Authors: Stephan Eckstein, Michael Kupper 
Publication date: 23 April 2021
Published in: Applied Mathematics and Optimization (Search for Journal in Brave)
Abstract: 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 the optimization problem in its dual formulation and reduce it to a finite dimensional one which corresponds to optimizing a neural network with smooth objective function. We present numerical examples from optimal transport, martingale optimal transport, portfolio optimization under uncertainty and generative adversarial networks that showcase the generality and effectiveness of the approach.
Full work available at URL: https://arxiv.org/abs/1802.08539
Recommendations
- Robust pricing and hedging of options on multiple assets and its numerics
- Computational methods for martingale optimal transport problems
- Entropy martingale optimal transport and nonlinear pricing-hedging duality
- Approximation of optimal transport problems with marginal moments constraints
- Iterative Bregman projections for regularized transportation problems
optimal transportdualityKnightian uncertaintynumerical methodregularisationdistributional robustnessrobust hedgingfeedforward networks
Optimal transportation (49Q22) Neural networks for/in biological studies, artificial life and related topics (92B20)
Cites Work
- Coherent measures of risk
- Optimal Transport
- Convolutional Wasserstein distances: efficient optimal transportation on geometric domains
- Computation of sharp bounds on the distribution of a function of dependent risks
- Stochastic finance. An introduction in discrete time.
- \(G\)-expectation, \(G\)-Brownian motion and related stochastic calculus of Itô type
- Title not available (Why is that?)
- Risk aggregation with dependence uncertainty
- A stochastic control approach to no-arbitrage bounds given marginals, with an application to lookback options
- Duality theorems for marginal problems
- Model-independent bounds for option prices -- a mass transport approach
- AUTOMATED OPTION PRICING: NUMERICAL METHODS
- The Existence of Probability Measures with Given Marginals
- Iterative Bregman projections for regularized transportation problems
- A survey of the Schrödinger problem and some of its connections with optimal transport
- AN OLD‐NEW CONCEPT OF CONVEX RISK MEASURES: THE OPTIMIZED CERTAINTY EQUIVALENT
- Calculation of the Wasserstein Distance Between Probability Distributions on the Line
- Multistage stochastic optimization
- Duality Formulas for Robust Pricing and Hedging in Discrete Time
- Asymptotic analysis of the exponential penalty trajectory in linear programming
- Duality for increasing convex functionals with countably many marginal constraints
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- Improved Fréchet-Hoeffding bounds on \(d\)-copulas and applications in model-free finance
- Sampling of one-dimensional probability measures in the convex order and computation of robust option price bounds
- Convergence of entropic schemes for optimal transport and gradient flows
- Smoothing operators in multi-marginal optimal transport
- Acceptance–Rejection Sampling Made Easy
- Constrained optimal transport
- Computational methods for martingale optimal transport problems
- Stabilized Sparse Scaling Algorithms for Entropy Regularized Transport Problems
- Deep hedging
- Robust risk aggregation with neural networks
Cited In (13)
- Detecting data-driven robust statistical arbitrage strategies with deep neural networks
- Model-free price bounds under dynamic option trading
- Deep learning for constrained utility maximisation
- Robust statistical arbitrage strategies
- A multi-marginal c-convex duality theorem for martingale optimal transport
- General construction and classes of explicit \(L^1\)-optimal couplings
- Connecting GANs, mean-field games, and optimal transport
- A Scalable Deep Learning Approach for Solving High-Dimensional Dynamic Optimal Transport
- Improved robust price bounds for multi-asset derivatives under market-implied dependence information
- Neural networks can detect model-free static arbitrage strategies
- Stability and sample complexity of divergence regularized optimal transport
- Applications of weak transport theory
- Martingale transport with homogeneous stock movements
Uses Software
This page was built for publication: Computation of optimal transport and related hedging problems via penalization and neural networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2020305)
