A Refined Parameter Condition in the Lyapunov Analysis of IGAHD
Abstract
In a recent paper, Attouch, Chbani, Fadili and Riahi introduced the inertial gradient algorithm with Hessian-driven daming, called (IGAHD). Under the condition 0≤β<2√s, where β is the Hessian driven damping parameter and s>0 is the gradient step size, their Lyapunov analysis shows an accelerated estimate of the objective function as well as a weighted summability of the gradient for the case β>0. For any fixed value of β>0, this condition excluded sufficiently small step sizes s>0. The present note refines one of the estimates in this Lyapunov analysis by retaining two coefficients that were previously replaced by lower bounds. This leads to the following less restrictive and sufficient condition: 0<βL√s<1+√(1+sL(1−sL)), where L>0 is the constant Lipschitz of the gradient objective function and 0<s≤1/L. In particular, the simplest condition 0<β<2/L√s is sufficient. For fixed values of β>0 and L>0, this new condition is satisfied for sufficiently small s>0. Consequently, under this new refined sufficient condition, the conclusions in the original paper stay valid. For convex quadratic functions in finite dimensions, a separate spectral analysis leads to a larger region parameters. It gives a necessary and sufficient condition for Schur stability of the limit modal matrices, as well as the geometrical decay of the objective residuals and the gradients. This modal analysis raises the question of whether a different Lyapunov function would allow us to recover part (or all) of this extended spectral domain for non-quadratic objective functions.
Related
- Kernel Methods for Refined Prophet Inequalities
- Refined proper descent for left completed sheaves on locally compact Hausdorff spaces
- REFINED MODULAR SYMBOLS AND REFINED EISENSTEIN IDEALS
- Pointwise Hölder continuity of Lyapunov exponents of random matrix products
- Local Smoothing Estimates of Schrödinger Operators on Waveguides Using Refined Decoupling
BibTeX
@misc{adly2026refined,
title = {{A Refined Parameter Condition in the Lyapunov Analysis of IGAHD}},
author = {Samir Adly},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2608.28088},
eprint = {2608.28088},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.28088},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - A Refined Parameter Condition in the Lyapunov Analysis of IGAHD
AU - Samir Adly
PY - 2026
DA - 2026/08/28
PB - arXiv
DO - 10.48550/arxiv.2608.28088
UR - https://arxiv.org/abs/2608.28088
AB - In a recent paper, Attouch, Chbani, Fadili and Riahi introduced the inertial gradient algorithm with Hessian-driven daming, called (IGAHD). Under the condition 0≤β<2√s, where β is the Hessian driven damping parameter and s>0 is the gradient step size, their Lyapunov analysis shows an accelerated estimate of the objective function as well as a weighted summability of the gradient for the case β>0. For any fixed value of β>0, this condition excluded sufficiently small step sizes s>0. The present note refines one of the estimates in this Lyapunov analysis by retaining two coefficients that were previously replaced by lower bounds. This leads to the following less restrictive and sufficient condition: 0<βL√s<1+√(1+sL(1−sL)), where L>0 is the constant Lipschitz of the gradient objective function and 0<s≤1/L. In particular, the simplest condition 0<β<2/L√s is sufficient. For fixed values of β>0 and L>0, this new condition is satisfied for sufficiently small s>0. Consequently, under this new refined sufficient condition, the conclusions in the original paper stay valid. For convex quadratic functions in finite dimensions, a separate spectral analysis leads to a larger region parameters. It gives a necessary and sufficient condition for Schur stability of the limit modal matrices, as well as the geometrical decay of the objective residuals and the gradients. This modal analysis raises the question of whether a different Lyapunov function would allow us to recover part (or all) of this extended spectral domain for non-quadratic objective functions.
ER -