Sharpness, Restart and Acceleration - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles SIAM Journal on Optimization Year : 2020

Sharpness, Restart and Acceleration

Abstract

The Łojasiewicz inequality shows that sharpness bounds on the minimum of convex optimization problems hold almost generically. Sharpness directly controls the performance of restart schemes, as observed by Nemirovskii and Nesterov [1985]. The constants quantifying these sharpness bounds are of course unobservable , but we show that optimal restart strategies are robust, in the sense that, in some important cases, finding the best restart scheme only requires a log scale grid search. Overall then, restart schemes generically accelerate accelerated first-order methods.
Fichier principal
Vignette du fichier
1702.03828.pdf (359.08 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-02983236 , version 1 (29-10-2020)

Identifiers

Cite

Vincent Roulet, Alexandre d'Aspremont. Sharpness, Restart and Acceleration. SIAM Journal on Optimization, 2020, 30 (1), pp.262-289. ⟨10.1137/18M1224568⟩. ⟨hal-02983236⟩
2033 View
158 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More