English

Neural network approximation for superhedging prices

Mathematical Finance 2021-07-30 v1

Abstract

This article examines neural network-based approximations for the superhedging price process of a contingent claim in a discrete time market model. First we prove that the α\alpha-quantile hedging price converges to the superhedging price at time 00 for α\alpha tending to 11, and show that the α\alpha-quantile hedging price can be approximated by a neural network-based price. This provides a neural network-based approximation for the superhedging price at time 00 and also the superhedging strategy up to maturity. To obtain the superhedging price process for t>0t>0, by using the Doob decomposition it is sufficient to determine the process of consumption. We show that it can be approximated by the essential supremum over a set of neural networks. Finally, we present numerical results.

Keywords

Cite

@article{arxiv.2107.14113,
  title  = {Neural network approximation for superhedging prices},
  author = {Francesca Biagini and Lukas Gonon and Thomas Reitsam},
  journal= {arXiv preprint arXiv:2107.14113},
  year   = {2021}
}
R2 v1 2026-06-24T04:39:24.791Z