Saved in:
Bibliographic Details
Main Authors: Adly, Samir, Ho, Vinh Thanh, Nguyen, Huu Nhan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.23035
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911411307806720
author Adly, Samir
Ho, Vinh Thanh
Nguyen, Huu Nhan
author_facet Adly, Samir
Ho, Vinh Thanh
Nguyen, Huu Nhan
contents In this paper, we study an explicit Tikhonov-regularized inertial gradient algorithm for smooth convex minimization with Lipschitz continuous gradient. The method is derived via an explicit time discretization of a damped inertial system with vanishing Tikhonov regularization. Under appropriate control of the decay rate of the Tikhonov term, we establish accelerated convergence of the objective values to the minimum together with strong convergence of the iterates to the minimum-norm minimizer. In particular, for polynomial schedules $\varepsilon_k = k^{-p}$ with $0<p<2$, we prove strong convergence to the minimum-norm solution while preserving fast objective decay. In the critical case $p=2$, we still obtain fast rates for the objective values, while our analysis does not guarantee strong convergence to the minimum-norm minimizer. Furthermore, we provide a thorough theoretical analysis for several choices of Tikhonov schedules. Numerical experiments on synthetic, benchmark, and real datasets illustrate the practical performance of the proposed algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_2601_23035
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Accelerated Inertial Gradient Algorithms with Vanishing Tikhonov Regularization
Adly, Samir
Ho, Vinh Thanh
Nguyen, Huu Nhan
Optimization and Control
In this paper, we study an explicit Tikhonov-regularized inertial gradient algorithm for smooth convex minimization with Lipschitz continuous gradient. The method is derived via an explicit time discretization of a damped inertial system with vanishing Tikhonov regularization. Under appropriate control of the decay rate of the Tikhonov term, we establish accelerated convergence of the objective values to the minimum together with strong convergence of the iterates to the minimum-norm minimizer. In particular, for polynomial schedules $\varepsilon_k = k^{-p}$ with $0<p<2$, we prove strong convergence to the minimum-norm solution while preserving fast objective decay. In the critical case $p=2$, we still obtain fast rates for the objective values, while our analysis does not guarantee strong convergence to the minimum-norm minimizer. Furthermore, we provide a thorough theoretical analysis for several choices of Tikhonov schedules. Numerical experiments on synthetic, benchmark, and real datasets illustrate the practical performance of the proposed algorithm.
title Accelerated Inertial Gradient Algorithms with Vanishing Tikhonov Regularization
topic Optimization and Control
url https://arxiv.org/abs/2601.23035