Global Convergence of Control-Based Lagrangian Flows for Non-Convex Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pirrera, Simone, Ripa, Francesco, Astolfi, Daniele, Cerone, Vito, Fosson, Sophie M., Regruto, Diego
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911715193520128
author Pirrera, Simone
Ripa, Francesco
Astolfi, Daniele
Cerone, Vito
Fosson, Sophie M.
Regruto, Diego
author_facet Pirrera, Simone
Ripa, Francesco
Astolfi, Daniele
Cerone, Vito
Fosson, Sophie M.
Regruto, Diego
contents This paper studies the continuous-time dynamics generated by control-theoretic Lagrangian methods for equality-constrained optimization. In particular, we consider dynamics induced by proportional-integral and feedback linearization controllers, which have recently been proposed as alternatives to primal-dual gradient methods. Unlike global convergence results for these dynamics, which rely on strong convexity of the objective function or boundedness assumptions, we exploit the geometric structure induced by the constraints. Specifically, we show global exponential convergence for non-convex problems that satisfy a suitable convexity property when restricted to the constraint manifold.
format Preprint
id arxiv_https___arxiv_org_abs_2605_22486
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Global Convergence of Control-Based Lagrangian Flows for Non-Convex Optimization
Pirrera, Simone
Ripa, Francesco
Astolfi, Daniele
Cerone, Vito
Fosson, Sophie M.
Regruto, Diego
Optimization and Control
Systems and Control
This paper studies the continuous-time dynamics generated by control-theoretic Lagrangian methods for equality-constrained optimization. In particular, we consider dynamics induced by proportional-integral and feedback linearization controllers, which have recently been proposed as alternatives to primal-dual gradient methods. Unlike global convergence results for these dynamics, which rely on strong convexity of the objective function or boundedness assumptions, we exploit the geometric structure induced by the constraints. Specifically, we show global exponential convergence for non-convex problems that satisfy a suitable convexity property when restricted to the constraint manifold.
title Global Convergence of Control-Based Lagrangian Flows for Non-Convex Optimization
topic Optimization and Control
Systems and Control
url https://arxiv.org/abs/2605.22486