A hierarchy of convex relaxations for the total variation distance

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autor principal: Lasserre, Jean-Bernard
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915556216537088
author Lasserre, Jean-Bernard
author_facet Lasserre, Jean-Bernard
contents 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 $μ$-$ν$.
format Preprint
id arxiv_https___arxiv_org_abs_2401_01086
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A hierarchy of convex relaxations for the total variation distance
Lasserre, Jean-Bernard
Optimization and Control
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 $μ$-$ν$.
title A hierarchy of convex relaxations for the total variation distance
topic Optimization and Control
url https://arxiv.org/abs/2401.01086