Constrained Optimization from a Control Perspective via Feedback Linearization
Abstract
Tools from control and dynamical systems have proven valuable for analyzing and developing optimization methods. In this paper, we establish rigorous theoretical foundations for using feedback linearization—a well-established nonlinear control technique—to solve constrained optimization problems. For equality-constrained optimization, we establish global convergence rates to first-order Karush-Kuhn-Tucker (KKT) points and uncover the close connection between the FL method and the Sequential Quadratic Programming (SQP) algorithm. Building on this relationship, we extend the FL approach to handle inequality-constrained problems. Furthermore, we introduce a momentum-accelerated feedback linearization algorithm and provide a rigorous convergence guarantee.
Cite
Text
Zhang et al. "Constrained Optimization from a Control Perspective via Feedback Linearization." Advances in Neural Information Processing Systems, 2025.Markdown
[Zhang et al. "Constrained Optimization from a Control Perspective via Feedback Linearization." Advances in Neural Information Processing Systems, 2025.](https://mlanthology.org/neurips/2025/zhang2025neurips-constrained/)BibTeX
@inproceedings{zhang2025neurips-constrained,
title = {{Constrained Optimization from a Control Perspective via Feedback Linearization}},
author = {Zhang, Runyu and Raghunathan, Arvind and Shamma, Jeff S and Li, Na},
booktitle = {Advances in Neural Information Processing Systems},
year = {2025},
url = {https://mlanthology.org/neurips/2025/zhang2025neurips-constrained/}
}