Model identification and local linear convergence of coordinate descent - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Preprints, Working Papers, ... Year : 2020

Model identification and local linear convergence of coordinate descent

Abstract

For composite nonsmooth optimization problems, Forward-Backward algorithm achieves model identification (e.g., support identification for the Lasso) after a finite number of iterations, provided the objective function is regular enough. Results concerning coordinate descent are scarcer and model identification has only been shown for specific estimators, the support-vector machine for instance. In this work, we show that cyclic coordinate descent achieves model identification in finite time for a wide class of functions. In addition, we prove explicit local linear convergence rates for coordinate descent. Extensive experiments on various estimators and on real datasets demonstrate that these rates match well empirical results.
Fichier principal
Vignette du fichier
suppid_arxiv.pdf (592.77 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03019711 , version 1 (23-11-2020)

Identifiers

  • HAL Id : hal-03019711 , version 1

Cite

Quentin Klopfenstein, Quentin Bertrand, Alexandre Gramfort, Joseph Salmon, Samuel Vaiter. Model identification and local linear convergence of coordinate descent. 2020. ⟨hal-03019711⟩
70 View
51 Download

Share

Gmail Facebook X LinkedIn More