Convergence rates of an inertial gradient descent algorithm under growth and flatness conditions - Archive ouverte HAL Access content directly
Journal Articles Mathematical Programming Year : 2020

Convergence rates of an inertial gradient descent algorithm under growth and flatness conditions

Abstract

In this paper we study the convergence properties of a Nesterov’s family of inertial schemes which is a specific case of inertial Gradient Descent algorithm in the context of a smooth convex minimization problem, under some additional hypotheses on the local geometry of the objective function F, such as the growth (or Łojasiewicz) condition. In particular we study the different convergence rates for the objective function and the local variation, depending on these geometric conditions. In this setting we can give optimal convergence rates for this Nesterov scheme. Our analysis shows that there are some situations when Nesterov’s family of inertial schemes is asymptotically less efficient than the gradient descent (e.g. in the case when the objective function is quadratic).
Fichier principal
Vignette du fichier
iGDgeometrybis.pdf (1.09 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01965095 , version 1 (24-12-2018)
hal-01965095 , version 2 (05-04-2019)
hal-01965095 , version 3 (19-09-2019)

Identifiers

Cite

Vassilis Apidopoulos, Jean-François Aujol, Charles H Dossal, Aude Rondepierre. Convergence rates of an inertial gradient descent algorithm under growth and flatness conditions. Mathematical Programming, 2020, ⟨10.1007/s10107-020-01476-3⟩. ⟨hal-01965095v3⟩
461 View
874 Download

Altmetric

Share

Gmail Facebook X LinkedIn More