Fully Probabilistic Design for Optimal Transport

TL;DR

This paper introduces a new theoretical framework called FPD-OT that unifies Optimal Transport with Fully Probabilistic Design, enabling the incorporation of probabilistic constraints and uncertainty quantification for more robust solutions.

Contribution

It establishes a formal connection between Optimal Transport and Fully Probabilistic Design, extending OT to handle probabilistic constraints and uncertainty.

Findings

OT is shown to be an instance of FPD.

The extended FPD-OT framework allows for probabilistic constraints.

Provides a foundation for robust OT solutions under uncertainty.

Abstract

The goal of this paper is to introduce a new theoretical framework for Optimal Transport (OT), using the terminology and techniques of Fully Probabilistic Design (FPD). Optimal Transport is the canonical method for comparing probability measures and has been successfully applied in a wide range of areas (computer vision Rubner et al. [2004], computer graphics Solomon et al. [2015], natural language processing Kusner et al. [2015], etc.). However, we argue that the current OT framework suffers from two shortcomings: first, it is hard to induce generic constraints and probabilistic knowledge in the OT problem; second, the current formalism does not address the question of uncertainty in the marginals, lacking therefore the mechanisms to design robust solutions. By viewing the OT problem as the optimal design of a probability density function with marginal constraints, we prove that OT is an instance of the more generic FPD framework. In this new setting, we can furnish the OT framework with the necessary mechanisms for processing probabilistic constraints and deriving uncertainty quantifiers, hence establishing a new extended framework, called FPD-OT. Our main contribution in this paper is to establish the connection between OT and FPD, providing new theoretical insights for both. This will lay the foundations for the application of FPD-OT in a subsequent work, notably in processing more sophisticated knowledge constraints, as well as in designing robust solutions in the case of uncertain marginals.