Skip to Main content Skip to Navigation
Journal articles

Convergence rates of damped inertial dynamics under geometric conditions

Abstract : In this article a family of second order ODEs associated to inertial gradient descend is studied. These ODEs are widely used to build trajectories converging to a minimizer x* of a function F , possibly convex. This family includes the continuous version of the Nesterov inertial scheme and the continuous heavy ball method. Several damping parameters, not necessarily vanishing, and a perturbation term g are thus considered. The damping parameter is linked to the inertia of the associated inertial scheme and the perturbation term g is linked to the error that can be done on the gradient of the function F. This article presents new asymptotic bounds on F(x(t)) − F (x*) where x is a solution of the ODE, when F is convex and satisfies local geometrical properties such as Łojasiewicz properties and under integrability conditions on g. Even if geometrical properties and perturbations were already studied for most ODEs of these families, it is the first time they are jointly studied. All these results give an insight on the behavior of these inertial and perturbed algorithms if F satisfies some Łojasiewicz properties especially in the setting of stochastic algorithms.
Document type :
Journal articles
Complete list of metadata

Cited literature [27 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02173978
Contributor : Aude Rondepierre Connect in order to contact the contributor
Submitted on : Wednesday, May 20, 2020 - 9:34:50 PM
Last modification on : Wednesday, November 3, 2021 - 8:50:28 AM

File

analysis_ode_Nesterov_HB_v3.pd...
Files produced by the author(s)

Identifiers

Citation

Othmane Sebbouh, Charles Dossal, Aude Rondepierre. Convergence rates of damped inertial dynamics under geometric conditions. SIAM Journal on Optimization, Society for Industrial and Applied Mathematics, 2020, 30 (3), pp.1850-1877. ⟨10.1137/19M1272767⟩. ⟨hal-02173978v3⟩

Share

Metrics

Record views

153

Files downloads

263