Smooth and Sparse Optimal Transport

TL;DR

This paper introduces a regularization framework for optimal transport that promotes sparsity in transportation plans, providing theoretical bounds and applications like color transfer, improving over entropic regularization.

Contribution

It proposes strongly convex regularizations for primal and dual OT to achieve sparse and group-sparse plans, with theoretical error bounds and practical applications.

Findings

Squared 2-norm regularization often yields smaller approximation errors than entropic regularization.

The framework enables sparse and group-sparse transportation plans.

Application demonstrated on color transfer task.

Abstract

Entropic regularization is quickly emerging as a new standard in optimal transport (OT). It enables to cast the OT computation as a differentiable and unconstrained convex optimization problem, which can be efficiently solved using the Sinkhorn algorithm. However, entropy keeps the transportation plan strictly positive and therefore completely dense, unlike unregularized OT. This lack of sparsity can be problematic in applications where the transportation plan itself is of interest. In this paper, we explore regularizing the primal and dual OT formulations with a strongly convex term, which corresponds to relaxing the dual and primal constraints with smooth approximations. We show how to incorporate squared $2$-norm and group lasso regularizations within that framework, leading to sparse and group-sparse transportation plans. On the theoretical side, we bound the approximation error introduced by regularizing the primal and dual formulations. Our results suggest that, for the regularized primal, the approximation error can often be smaller with squared $2$-norm than with entropic regularization. We showcase our proposed framework on the task of color transfer.