Finite-Time Optimization via Scaled Gradient-Momentum Flows
Optimization and Control
2026-04-15 v1 Systems and Control
Systems and Control
Abstract
In this paper, we develop a scaled gradient-momentum framework for continuous-time optimization that achieves global finite-time convergence. A state-dependent scaling mechanism is introduced to enable classical dynamics, such as Heavy-Ball-type and proportional-integral (PI)-type flows, to attain finite-time convergence. We establish explicit conditions that bridge the gradient-dominance property of the objective function and finite-time stability of the proposed scaled dynamics. Numerical experiments validate the theoretical results.
Cite
@article{arxiv.2604.12751,
title = {Finite-Time Optimization via Scaled Gradient-Momentum Flows},
author = {Yu Zhou and Mengmou Li and Masaaki Nagahara},
journal= {arXiv preprint arXiv:2604.12751},
year = {2026}
}