
Local Linear Convergence of Inertial Forward-Backward Splitting for Low Complexity Regularization
Liang, Jingwei; Fadili, Jalal M.; Peyré, Gabriel (2015), Local Linear Convergence of Inertial Forward-Backward Splitting for Low Complexity Regularization, SPARS, 2015, Cambridge, United Kingdom
View/ Open
Type
Communication / ConférenceDate
2015Conference title
SPARSConference date
2015Conference city
CambridgeConference country
United KingdomMetadata
Show full item recordAuthor(s)
Liang, JingweiGroupe de Recherche en Informatique, Image et Instrumentation de Caen [GREYC]
Fadili, Jalal M.
Groupe de Recherche en Informatique, Image et Instrumentation de Caen [GREYC]
Peyré, Gabriel
CEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
Abstract (EN)
In this abstract, we consider the inertial Forward-Backward (iFB) splitting method and its special cases (Forward-Backward/ISTA and FISTA). Under the assumption that the non-smooth part of the objective is partly smooth relative to an active smooth manifold, we show that iFB-type methods (i) identify the active manifold in finite time, then (ii) enter a local linear convergence regime that we characterize precisely. This gives a grounded and unified explanation to the typical behaviour that has been observed numerically for many low-complexity regularizers, including 1 , 1,2-norms, total variation (TV) and nuclear norm to name a few. The obtained results are illustrated by concrete examples.Subjects / Keywords
Forward-Backward SplittingRelated items
Showing items related by title and author.
-
Liang, Jingwei; Fadili, Jalal; Peyré, Gabriel (2014) Communication / Conférence
-
Liang, Jingwei; Fadili, Jalal M.; Peyré, Gabriel; Luke, Russell (2015) Communication / Conférence
-
Liang, Jingwei; Fadili, Jalal; Peyré, Gabriel (2014) Communication / Conférence
-
Liang, Jingwei; Fadili, Jalal; Peyré, Gabriel (2018) Article accepté pour publication ou publié
-
Liang, Jingwei; Fadili, Jalal; Peyré, Gabriel; Luke, Russell (2015) Communication / Conférence