Bicausal Optimal Transport for Markov Chains via Dynamic Programming

TL;DR

This paper introduces a bicausal optimal transport framework for Markov chains, leveraging Markov decision processes to derive optimality conditions and algorithms, with applications to concentration of measure.

Contribution

It develops a novel bicausal optimal transport formulation for Markov chains, connecting it to Markov decision processes and classical coupling theory, with practical algorithms.

Findings

Derived necessary and sufficient conditions for optimality.

Proposed an iterative value iteration algorithm for transport cost.

Linked transportation cost to concentration of measure in Markov chains.

Abstract

In this paper we study the bicausal optimal transport problem for Markov chains, an optimal transport formulation suitable for stochastic processes which takes into consideration the accumulation of information as time evolves. Our analysis is based on a relation between the transport problem and the theory of Markov decision processes. This way we are able to derive necessary and sufficient conditions for optimality in the transport problem, as well as an iterative algorithm, namely the value iteration, for the calculation of the transportation cost. Additionally, we draw the connection with the classic theory on couplings for Markov chains, and in particular with the notion of faithful couplings. Finally, we illustrate how the transportation cost appears naturally in the study of concentration of measure for Markov chains.