Skip to Main content Skip to Navigation
New interface
Preprints, Working Papers, ... (Preprint)

Accelerated gradient methods with strong convergence to the minimum norm minimizer: a dynamic approach combining time scaling, averaging, and Tikhonov regularization

Abstract : In a Hilbert framework, for convex differentiable optimization, we consider accelerated gradient methods obtained by combining temporal scaling and averaging techniques with Tikhonov regularization. We start from the continuous steepest descent dynamic with an additional Tikhonov regularization term whose coefficient vanishes asymptotically. We provide an extensive Lyapunov analysis of this first-order evolution equation. Then we apply to this dynamic the method of time scaling and averaging recently introduced by Attouch, Bot and Nguyen. We thus obtain an inertial dynamic which involves viscous damping associated with Nesterov's method, implicit Hessian damping and Tikhonov regularization. Under an appropriate setting of the parameters, just using Jensen's inequality, without the need for another Lyapunov analysis, we show that the trajectories have at the same time several remarkable properties: they provide a rapid convergence of values, fast convergence of the gradients to zero, and strong convergence to the minimum norm minimizer. These results complete and improve the previous results obtained by the authors.
Document type :
Preprints, Working Papers, ... (Preprint)
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03859665
Contributor : Hedy Attouch Connect in order to contact the contributor
Submitted on : Friday, November 18, 2022 - 12:26:08 PM
Last modification on : Friday, November 25, 2022 - 3:36:17 AM

File

ACR-TSA-Tikh-Nov-18-22.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03859665, version 1

Citation

Hedy Attouch, Zaki Chbani, Hassan Riahi. Accelerated gradient methods with strong convergence to the minimum norm minimizer: a dynamic approach combining time scaling, averaging, and Tikhonov regularization. 2022. ⟨hal-03859665⟩

Share

Metrics

Record views

0

Files downloads

0