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

02/23/2018
by   Stephan Eckstein, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/14/2023

Partial Neural Optimal Transport

We propose a novel neural method to compute partial optimal transport (O...
research
10/22/2020

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

We study MinMax solution methods for a general class of optimization pro...
research
12/20/2022

A Communication Optimal Transport Approach to the Computation of Rate Distortion Functions

In this paper, we propose a new framework named Communication Optimal Tr...
research
02/22/2020

Learning Cost Functions for Optimal Transport

Learning the cost function for optimal transport from observed transport...
research
01/03/2022

Faster Unbalanced Optimal Transport: Translation invariant Sinkhorn and 1-D Frank-Wolfe

Unbalanced optimal transport (UOT) extends optimal transport (OT) to tak...
research
05/25/2020

Feature Robust Optimal Transport for High-dimensional Data

Optimal transport is a machine learning technique with applications incl...
research
05/16/2022

A scalable deep learning approach for solving high-dimensional dynamic optimal transport

The dynamic formulation of optimal transport has attracted growing inter...

Please sign up or login with your details

Forgot password? Click here to reset