Sensitivity Analysis for Mirror-Stratifiable Convex Functions - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue SIAM Journal on Optimization Année : 2018

Sensitivity Analysis for Mirror-Stratifiable Convex Functions

Résumé

This paper provides a set of sensitivity analysis and activity identification results for a class of convex functions with a strong geometric structure, that we coined " mirror-stratifiable ". These functions are such that there is a bijection between a primal and a dual stratification of the space into partitioning sets, called strata. This pairing is crucial to track the strata that are identifiable by solutions of parametrized optimization problems or by iterates of optimization algorithms. This class of functions encompasses all regularizers routinely used in signal and image processing, machine learning, and statistics. We show that this " mirror-stratifiable " structure enjoys a nice sensitivity theory, allowing us to study stability of solutions of optimization problems to small perturbations , as well as activity identification of first-order proximal splitting-type algorithms. Existing results in the literature typically assume that, under a non-degeneracy condition, the active set associated to a minimizer is stable to small perturbations and is identified in finite time by optimization schemes. In contrast, our results do not require any non-degeneracy assumption: in consequence, the optimal active set is not necessarily stable anymore, but we are able to track precisely the set of identifiable strata.We show that these results have crucial implications when solving challenging ill-posed inverse problems via regularization, a typical scenario where the non-degeneracy condition is not fulfilled. Our theoretical results, illustrated by numerical simulations, allow to characterize the instability behaviour of the regularized solutions, by locating the set of all low-dimensional strata that can be potentially identified by these solutions. Key words. convex analysis, inverse problems, sensitivity, active sets, first-order algorithms, splitting algorithm, applications in imaging and machine learning
Fichier principal
Vignette du fichier
StratificationSensitivity.pdf (1.4 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01560130 , version 1 (11-07-2017)
hal-01560130 , version 2 (06-03-2019)

Identifiants

Citer

Jalal M. Fadili, Jérôme Malick, Gabriel Peyré. Sensitivity Analysis for Mirror-Stratifiable Convex Functions. SIAM Journal on Optimization, 2018, 28 (4), pp.2975-3000. ⟨10.1137/17M113825X⟩. ⟨hal-01560130v2⟩
419 Consultations
219 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More