Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Convergence of iterates for first-order optimization algorithms with inertia and Hessian driven damping

Abstract : In a Hilbert space setting, for convex optimization, we show the convergence of the iterates to optimal solutions for a class of accelerated first-order algorithms. They can be interpreted as discrete temporal versions of an inertial dynamic involving both viscous damping and Hessian-driven damping. The asymptotically vanishing viscous damping is linked to the accelerated gradient method of Nesterov while the Hessian driven damping makes it possible to significantly attenuate the oscillations. By treating the Hessian-driven damping as the time derivative of the gradient term, this gives, in discretized form, first-order algorithms. These results complement the previous work of the authors where it was shown the fast convergence of the values, and the fast convergence towards zero of the gradients. KEYWORDS Convergence of iterates; Hessian driven damping; inertial optimization algorithms; Nesterov accelerated gradient method; time rescaling.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03285272
Contributor : Jalal Fadili Connect in order to contact the contributor
Submitted on : Tuesday, July 13, 2021 - 11:23:37 AM
Last modification on : Wednesday, September 15, 2021 - 12:08:03 PM

File

ACFR_iteres_Optimization_July_...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03285272, version 1

Citation

Hédy Attouch, Zaki Chbani, Jalal M. Fadili, Hassan Riahi. Convergence of iterates for first-order optimization algorithms with inertia and Hessian driven damping. 2021. ⟨hal-03285272⟩

Share

Metrics

Record views

28

Files downloads

24