Skip to Main content Skip to Navigation
Reports

Convergence rates of the Heavy-Ball method with Lojasiewicz property

Abstract : In this paper, a joint study of the behavior of solutions of the Heavy Ball ODE and Heavy Ball type algorithms is given. Since the pioneering work of B.T. Polyak [38], it is well known that such a scheme is very efficient for C 2 strongly convex functions with Lipschitz gradient. But much less is known when only growth conditions are considered. Depending on the geometry of the function to minimize, convergence rates for convex functions, with some additional regularity such as quasi-strong convexity, or strong convexity, were recently obtained in [12]. Convergence results with much weaker assumptions are given in the present paper: namely, linear convergence rates when assuming a growth condition (which amounts to a Lojasiewicz property in the convex case). This analysis is firstly performed in continuous time for the ODE, and then transposed for discrete optimization schemes. In particular, a variant of the Heavy Ball algorithm is proposed, which converges geometrically whatever the parameters choice, and which has the best state of the art convergence rate for first order methods to minimize composite non smooth convex functions satisfying a Lojasiewicz property.
Document type :
Reports
Complete list of metadata

Cited literature [44 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02928958
Contributor : Jean-François Aujol Connect in order to contact the contributor
Submitted on : Thursday, September 3, 2020 - 9:32:24 AM
Last modification on : Wednesday, November 3, 2021 - 4:32:47 AM
Long-term archiving on: : Wednesday, December 2, 2020 - 6:02:07 PM

File

HeavyBall__growth_condition_.p...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02928958, version 1

Citation

J-F Aujol, Ch Dossal, Aude Rondepierre. Convergence rates of the Heavy-Ball method with Lojasiewicz property. [Research Report] IMB - Institut de Mathématiques de Bordeaux; INSA Toulouse; UPS Toulouse. 2020. ⟨hal-02928958⟩

Share

Metrics

Record views

209

Files downloads

372