A hierarchy of convex relaxations for the total variation distance - ANITI - Artificial and Natural Intelligence Toulouse Institute
Pré-Publication, Document De Travail Année : 2024

A hierarchy of convex relaxations for the total variation distance

Résumé

Given two measures µ, ν on Rd that satisfy Carleman's condition, we provide a numerical scheme to approximate as closely as desired the total variation distance between µ and ν. It consists of solving a sequence (hierarchy) of convex relaxations whose associated sequence of optimal values converges to the total variation distance, an additional illustration of the versatility of the Moment-SOS hierarchy. Indeed each relaxation in the hierarchy is a semidefinite program whose size increases with the number of involved moments. It has an optimal solution which is a couple of degree-2n pseudo-moments which converge, as n grows, to moments of the Hahn-Jordan decomposition of µ-ν.
Fichier principal
Vignette du fichier
TV2-arxiv.pdf (220.54 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04367575 , version 1 (30-12-2023)
hal-04367575 , version 2 (02-05-2024)
hal-04367575 , version 3 (20-09-2024)

Identifiants

Citer

Jean-Bernard Lasserre. A hierarchy of convex relaxations for the total variation distance. 2024. ⟨hal-04367575v2⟩
248 Consultations
41 Téléchargements

Altmetric

Partager

More