← Volver atrás
Publicaciones

Optimality Conditions for Bilevel Imaging Learning Problems with Total Variation Regularization

Autores

Carlos De los Reyes, Juan , VILLACIS PROAÑO, DAVID ALEJANDRO

Publicación externa

No

Medio

SIAM J. Imaging Sci.

Alcance

Article

Naturaleza

Científica

Cuartil JCR

1

Cuartil SJR

1

Impacto JCR

2.1

Impacto SJR

0.846

Fecha de publicacion

01/01/2022

ISI

000903981200003

Abstract

We address the problem of optimal scale-dependent parameter learning in total variation image de -noising. Such problems are formulated as bilevel optimization instances with total variation denoising problems as lower-level constraints. For the bilevel problem, we are able to derive M-stationarity conditions, after characterizing the corresponding Mordukhovich generalized normal cone and ver-ifying suitable constraint qualification conditions. We also derive B-stationarity conditions, after investigating the Lipschitz continuity and directional differentiability of the lower-level solution op-erator. A characterization of the Bouligand subdifferential of the solution mapping, by means of a properly defined linear system, is provided as well. Based on this characterization, we propose a two-phase nonsmooth trust-region algorithm for the numerical solution of the bilevel problem and test it computationally for two particular experimental settings.

Palabras clave

  bilevel optimization; machine learning; variational models; total variation

Miembros de la Universidad Loyola