The Equivalence of Fourier-based and Wasserstein Metrics on Imaging Problems

Autor:	Auricchio, Gennaro, Codegoni, Andrea, Gualandi, Stefano, Toscani, Giuseppe, Veneroni, Marco
Rok vydání:	2020
Předmět:	Mathematics - Optimization and Control Mathematical Physics Statistics - Machine Learning 90C06 90C08
Druh dokumentu:	Working Paper
Popis:	We investigate properties of some extensions of a class of Fourier-based probability metrics, originally introduced to study convergence to equilibrium for the solution to the spatially homogeneous Boltzmann equation. At difference with the original one, the new Fourier-based metrics are well-defined also for probability distributions with different centers of mass, and for discrete probability measures supported over a regular grid. Among other properties, it is shown that, in the discrete setting, these new Fourier-based metrics are equivalent either to the Euclidean-Wasserstein distance $W_2$, or to the Kantorovich-Wasserstein distance $W_1$, with explicit constants of equivalence. Numerical results then show that in benchmark problems of image processing, Fourier metrics provide a better runtime with respect to Wasserstein ones. Comment: 18 pages, 2 figures, 1 table
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2005.06530 Zobrazit plný text záznamu View this record from Arxiv