Convergence analysis of gradient flow for overparameterized LQR formulations

DOI10.1016/J.AUTOMATICA.2025.112504MaRDI QIDQ6929944zbMATH OpenFDO

Authors Arthur Castello B. De Oliveira, Milad Siami, Eduardo D. Sontag

Publication date 16 September 2025

Published in Automatica (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.AUTOMATICA.2025.112504

zbMATH Keywords

learning theoryinput-to-state stabilityapplication of nonlinear analysis and designoptimal control theorystability of nonlinear systemssingularities in optimization

Mathematics Subject Classification ID

Nonlinear systems in control theory (93C10) Input-output approaches in control theory (93D25)

Cites work

• scientific article; zbMATH DE number 3980094 (Why is no real title available?)
• scientific article; zbMATH DE number 3479763 (Why is no real title available?)
• scientific article; zbMATH DE number 7370615 (Why is no real title available?)
• scientific article; zbMATH DE number 3313108 (Why is no real title available?)
• A comparative analysis of reinforcement learning and adaptive control techniques for linear uncertain systems
• A geometric approach of gradient descent algorithms in linear neural networks
• Computational Design of Optimal Output Feedback Controllers
• Convergence and Sample Complexity of Gradient Methods for the Model-Free Linear–Quadratic Regulator Problem
• Cubic regularization of Newton method and its global performance
• Gradient descent only converges to minimizers: non-isolated critical points and invariant regions
• Learning Optimal Controllers for Linear Systems With Multiplicative Noise via Policy Gradient
• Learning deep linear neural networks: Riemannian gradient flows and convergence to global minimizers
• Remarks on input to state stability of perturbed gradient flows, motivated by model-free feedback control learning
• Small-disturbance input-to-state stability of perturbed gradient flows: applications to LQR problem
• Łojasiewicz inequalities and applications

This page was built for publication: Convergence analysis of gradient flow for overparameterized LQR formulations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6929944)