Computation of optimal transport and related hedging problems via penalization and neural networks
The core idea in this article 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. More precisely, the first step is to solve \[ \phi^m(f)=\inf _{\begin{array}{l} h\in H^m\\ h\ge f \end{array}} \int hd\mu_0 \] numerically, where \(H^m\) can be a set of neural networks with a fixed structure (but unspecified parameter values), and \(m\) measures the number of neurons per layer. To allow for a step-wise updating of the parameters (e.g. by gradient descent methods) for the space \(H^m\), the inequality constraint \(h\ge f\) is penalized. To this end, a reference probability measure \(\theta\) on the state space \(X\) is introduced. This leads to the penalized problem \[ \phi^m_{\theta,\beta}(f)=\inf _{h\in H^m}\{\int hd\mu_0+\int \beta (f-h)d\theta \}. \] 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 are given.
- 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
- G-expectation, G-Brownian motion and related stochastic calculus of Itô type
- A stochastic control approach to no-arbitrage bounds given marginals, with an application to lookback options
- A survey of the Schrödinger problem and some of its connections with optimal transport
- Acceptance–Rejection Sampling Made Easy
- AN OLD‐NEW CONCEPT OF CONVEX RISK MEASURES: THE OPTIMIZED CERTAINTY EQUIVALENT
- Asymptotic analysis of the exponential penalty trajectory in linear programming
- AUTOMATED OPTION PRICING: NUMERICAL METHODS
- Calculation of the Wasserstein Distance Between Probability Distributions on the Line
- Coherent measures of risk
- Computation of sharp bounds on the distribution of a function of dependent risks
- Computational methods for martingale optimal transport problems
- Constrained optimal transport
- Convergence of entropic schemes for optimal transport and gradient flows
- Convolutional Wasserstein distances: efficient optimal transportation on geometric domains
- Deep hedging
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- Duality for increasing convex functionals with countably many marginal constraints
- Duality Formulas for Robust Pricing and Hedging in Discrete Time
- Duality theorems for marginal problems
- scientific article; zbMATH DE number 3099866 (Why is no real title available?)
- Improved Fréchet-Hoeffding bounds on d-copulas and applications in model-free finance
- Iterative Bregman projections for regularized transportation problems
- Model-independent bounds for option prices -- a mass transport approach
- Multistage stochastic optimization
- Optimal Transport
- Risk aggregation with dependence uncertainty
- Robust risk aggregation with neural networks
- Sampling of one-dimensional probability measures in the convex order and computation of robust option price bounds
- Smoothing operators in multi-marginal optimal transport
- Stabilized Sparse Scaling Algorithms for Entropy Regularized Transport Problems
- Stochastic finance. An introduction in discrete time.
- The Existence of Probability Measures with Given Marginals
- Applications of weak transport theory
- General construction and classes of explicit \(L^1\)-optimal couplings
- Deep learning for constrained utility maximisation
- Martingale transport with homogeneous stock movements
- Robust statistical arbitrage strategies
- Model-free price bounds under dynamic option trading
- A Scalable Deep Learning Approach for Solving High-Dimensional Dynamic Optimal Transport
- Detecting data-driven robust statistical arbitrage strategies with deep neural networks
- A multi-marginal c-convex duality theorem for martingale optimal transport
- Connecting GANs, mean-field games, and 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
- A parametric approach to the estimation of convex risk functionals based on Wasserstein distance
- Computation of robust option prices via structured multimarginal martingale optimal transport
- Fitted value iteration methods for bicausal optimal transport
- Monotonicity in quadratically regularized linear programs
- Quantitative convergence of quadratically regularized linear programs
- Quadratically regularized optimal transport: existence and multiplicity of potentials
- Risk measures based on weak optimal transport
- The McCormick martingale optimal transport
- Exponential convergence of general iterative proportional fitting procedures
- Structural properties of multi-period martingale optimal transport problems and applications
- Sparsity of quadratically regularized optimal transport: scalar case
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)
