Regularized Optimal Transport is Ground Cost Adversarial
This offers a new theoretical perspective on regularization in optimal transport, potentially benefiting machine learning applications, but it appears incremental as it builds on existing regularization concepts.
The authors reinterpret convex regularization of optimal transport as a robust mechanism, showing it can be viewed as ground cost adversarial, which provides a robust dissimilarity measure for applications.
Regularizing the optimal transport (OT) problem has proven crucial for OT theory to impact the field of machine learning. For instance, it is known that regularizing OT problems with entropy leads to faster computations and better differentiation using the Sinkhorn algorithm, as well as better sample complexity bounds than classic OT. In this work we depart from this practical perspective and propose a new interpretation of regularization as a robust mechanism, and show using Fenchel duality that any convex regularization of OT can be interpreted as ground cost adversarial. This incidentally gives access to a robust dissimilarity measure on the ground space, which can in turn be used in other applications. We propose algorithms to compute this robust cost, and illustrate the interest of this approach empirically.