Screening Rules and its Complexity for Active Set Identification - Archive ouverte HAL Access content directly
Journal Articles Journal of Convex Analysis Year : 2021

Screening Rules and its Complexity for Active Set Identification

(1) , (2) , (3)
1
2
3

Abstract

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 and versions

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

Identifiers

Cite

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⟩
38 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More