On the Existence of Monge Maps for the Gromov-Wasserstein Problem
Abstract
In this work, we study the structure of minimizers of the quadratic Gromov--Wasserstein (GW) problem on Euclidean spaces for two different costs.
The first one is the scalar product for which we prove that it is always possible to find optimizers as Monge maps and we detail the structure of such optimal maps. The second cost is the squared Euclidean distance for which we show that the worst case scenario is the existence of a bi-map structure. Both results are direct and indirect consequences of an existence result of optimal maps in the standard optimal transportation problem for costs that are defined by submersions. In dimension one for the squared Euclidean distance, we show numerical evidence for a negative answer to the existence of a Monge map under the conditions of Brenier's theorem, suggesting that our result cannot be improved in general. In addition, we show that a monotone map is optimal in some non-symmetric situations, thereby giving insight on why such a map often appears to be optimal in numerical experiments.
Domains
General Mathematics [math.GM]
Origin : Files produced by the author(s)