Heavy Ball Momentum for Non-Strongly Convex Optimization - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2024

Heavy Ball Momentum for Non-Strongly Convex Optimization

Résumé

When considering the minimization of a quadratic or strongly convex function, it is well known that first-order methods involving an inertial term weighted by a constant-in-time parameter are particularly efficient (see Polyak [32], Nesterov [28], and references therein). By setting the inertial parameter according to the condition number of the objective function, these methods guarantee a fast exponential decay of the error. We prove that this type of schemes (which are later called Heavy Ball schemes) is relevant in a relaxed setting, i.e. for composite functions satisfying a quadratic growth condition. In particular, we adapt V-FISTA, introduced by Beck in [10] for strongly convex functions, to this broader class of functions. To the authors' knowledge, the resulting worst-case convergence rates are faster than any other in the literature, including those of FISTA restart schemes. No assumption on the set of minimizers is required and guarantees are also given in the non-optimal case, i.e. when the condition number is not exactly known. This analysis follows the study of the corresponding continuous-time dynamical system (Heavy Ball with friction system), for which new convergence results of the trajectory are shown.
Fichier principal
Vignette du fichier
manuscript_hal.pdf (620.43 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04500652 , version 1 (12-03-2024)

Identifiants

Citer

Jean-François Aujol, Charles Dossal, Hippolyte Labarrière, Aude Rondepierre. Heavy Ball Momentum for Non-Strongly Convex Optimization. 2024. ⟨hal-04500652⟩
7 Consultations
4 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More