Screening Rules and its Complexity for Active Set Identification - Département Image, Données, Signal Accéder directement au contenu
Article Dans Une Revue Journal of Convex Analysis Année : 2021

Screening Rules and its Complexity for Active Set Identification

Résumé

Screening rules were recently introduced as a technique for explicitly identifying active structures such as sparsity, in optimization problem arising in machine learning. This has led to new methods of acceleration based on a substantial dimension reduction. We show that screening rules stem from a combination of natural properties of subdifferential sets and optimality conditions, and can hence be understood in a unified way. Under mild assumptions, we analyze the number of iterations needed to identify the optimal active set for any converging algorithm. We show that it only depends on its convergence rate.

Dates et versions

hal-02933051 , version 1 (08-09-2020)

Identifiants

Citer

Eugene Ndiaye, Olivier Fercoq, Joseph Salmon. Screening Rules and its Complexity for Active Set Identification. Journal of Convex Analysis, 2021, 28 (4), pp.1053--1072. ⟨hal-02933051⟩
58 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More