The Monge optimal transport barycenter problem

TL;DR

This paper introduces an efficient, adversarial-based methodology for solving the Monge optimal transport barycenter problem, accommodating both discrete and continuous factors, with applications in density estimation and Bayesian inference.

Contribution

It develops a novel adversarial formulation for the Monge barycenter problem that is computationally efficient and applicable to complex multivariate scenarios.

Findings

Efficient gradient descent solution for the barycenter problem.

Extension to multivariate discrete and continuous factors.

Framework for density estimation and Bayesian inference.

Abstract

A novel methodology is developed for the solution of the data-driven Monge optimal transport barycenter problem, where the pushforward condition is formulated in terms of the statistical independence between two sets of random variables: the factors $z$ and a transformed outcome $y$. Relaxing independence to the uncorrelation between all functions of $z$ and $y$ within suitable finite-dimensional spaces leads to an adversarial formulation, for which the adversarial strategy can be found in closed form through the first principal components of a small-dimensional matrix. The resulting pure minimization problem can be solved very efficiently through gradient descent driven flows in phase space. The methodology extends beyond scenarios where only discrete factors affect the outcome, to multivariate sets of both discrete and continuous factors, for which the corresponding barycenter problems have infinitely many marginals. Corollaries include a new framework for the solution of the Monge optimal transport problem, a procedure for the data-based simulation and estimation of conditional probability densities, and a nonparametric methodology for Bayesian inference.