Thermodynamic interpretation of Wasserstein distance

Abstract

We derive a relation between the dissipation in a stochastic dynamics and the Wasserstein distance. We show that the minimal amount of dissipation required to transform an initial state to a final state during a diffusion process is given by the Wasserstein distance between the two states, divided by the total time of the process. This relation implies a lower bound on the dissipation for any diffusion process in terms of its initial and final state. Using a lower bound on the Wasserstein distance, we further show that we can give a lower bound on the dissipation in terms of only the mean and convariance matrix of the initial and final state. We apply this result to derive the optimal forces that minimize the dissipation for given initial and final mean and covariance.