Linearization of Monge-Amp\`ere Equations and Statistical Applications

TL;DR

This paper demonstrates that under certain regularity conditions, the curve of optimal transport maps is differentiable in time and its derivative solves a linearized Monge–Ampère equation, with implications for statistical applications.

Contribution

The work establishes the differentiability of optimal transport maps over time and characterizes their derivatives via a linearized Monge–Ampère equation, advancing theoretical understanding and applications.

Findings

The optimal transport map curve is ^1 in time under regularity conditions.

The time derivative of the transport map solves a linearized Monge–Ampère PDE.

Results enable regularity analysis and statistical inference for transport-based models.

Abstract

Optimal transport has found numerous applications across data science, many of which require differentiating the optimal transport map with respect to the underlying probability densities in the Fr\'echet sense. In this work, we show that when the reference measure $Q$ is sufficiently regular in space and the curve of target measures $\{P_t\}_{t\in I}$ is both spatially regular and $\mathcal{C}^1$ in time, then the associated curve of optimal transport maps $\{\nabla \phi_t\}_{t\in I}$ pushing $Q$ toward $P_t$ is itself a $\mathcal{C}^1$ curve. Moreover, we identify its time derivative as the solution to the \emph{linearized Monge--Amp\`ere equation}, a second-order elliptic PDE with strictly oblique boundary conditions and a vanishing zero-order term. Our proof relies on applying the implicit function theorem to the Monge--Amp\`ere equation with natural boundary conditions. As consequences, we establish regularity of the transport-based quantile regressor with respect to the covariates and derive a central limit theorem for smooth optimal transport maps.