(Martingale) Optimal Transport And Anomaly Detection With Neural Networks: A Primal-dual Algorithm
Optimization and Control
2019-04-12 v2 Computational Finance
Abstract
In this paper, we introduce a primal-dual algorithm for solving (martingale) optimal transportation problems, with cost functions satisfying the twist condition, close to the one that has been used recently for training generative adversarial networks. As some additional applications, we consider anomaly detection and automatic generation of financial data.
Cite
@article{arxiv.1904.04546,
title = {(Martingale) Optimal Transport And Anomaly Detection With Neural Networks: A Primal-dual Algorithm},
author = {Pierre Henry-Labordere},
journal= {arXiv preprint arXiv:1904.04546},
year = {2019}
}