We show convergence of the gradients of the Schrödinger potentials to the Brenier map in the small-time limit under general assumptions on the marginals, which allow for unbounded densities and supports. Furthermore, we provide novel quantitative stability estimates for the optimal values and optimal couplings for the Schrödinger problem (SP), that we express in terms of a negative order weighted homogeneous Sobolev norm. The latter encodes the linearized behavior of the 2-Wasserstein distance between the marginals. The proofs of both results highlight for the first time the relevance of gradient bounds for Schrödinger potentials, that we establish here in full generality, in the analysis of the short-time behavior of Schrödinger bridges. Finally, we discuss how our results translate into the framework of quadratic Entropic Optimal Transport, that is a version of SP more suitable for applications in machine learning and data science.
Chiarini, A., Conforti, G., Greco, G., Tamanini, L., Gradient estimates for the Schrödinger potentials: convergence to the Brenier map and quantitative stability, <<COMMUNICATIONS IN PARTIAL DIFFERENTIAL EQUATIONS>>, 2023; 48 (6): 895-943. [doi:10.1080/03605302.2023.2215527] [https://hdl.handle.net/10807/259301]
Gradient estimates for the Schrödinger potentials: convergence to the Brenier map and quantitative stability
Tamanini, Luca
2023
Abstract
We show convergence of the gradients of the Schrödinger potentials to the Brenier map in the small-time limit under general assumptions on the marginals, which allow for unbounded densities and supports. Furthermore, we provide novel quantitative stability estimates for the optimal values and optimal couplings for the Schrödinger problem (SP), that we express in terms of a negative order weighted homogeneous Sobolev norm. The latter encodes the linearized behavior of the 2-Wasserstein distance between the marginals. The proofs of both results highlight for the first time the relevance of gradient bounds for Schrödinger potentials, that we establish here in full generality, in the analysis of the short-time behavior of Schrödinger bridges. Finally, we discuss how our results translate into the framework of quadratic Entropic Optimal Transport, that is a version of SP more suitable for applications in machine learning and data science.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.