No Spurious Local Minima in Full-Order Linear Quadratic Gaussian Control

arXiv:2609.32875 · math.OC, cs.SY, eess.SY · Submitted 2026-09-26 · Read on arXiv

math.OC, cs.SY, eess.SY

Submitted: 2026-09-26

Updated: 2026-09-26

Terminology

• Closed-Loop System — 7× in this paper · explained in 4 episodes
• Linear Quadratic Gaussian — 5× in this paper
• American Control Conference — 3× in this paper
• Convergence Guarantees — 2× in this paper · explained in 3 episodes
• Frequency-Domain Analysis — 2× in this paper · explained in 2 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Sample Complexity — 2× in this paper · explained in 15 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• H2-norm — 1× in this paper · explained in 2 episodes
• Objective Function — 1× in this paper · explained in 2 episodes
• Regret — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• Policy Optimization in the Linear Quadratic Gaussian Problem: A Frequency Domain Perspective
• Gradient Dominance in the Linear Quadratic Regulator: A Unified Analysis for Continuous-Time and Discrete-Time Systems
• Policy Optimization of Mixed H2/H-infinity Control: Benign Nonconvexity and Global Optimality
• Model-free Online Learning for the Kalman Filter: Forgetting Factor and Logarithmic Regret

Related papers

• Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise
• Adam-HNAG: A Convergent Reformulation of Adam with Accelerated Rate
• Incremental Learning in Mirror Flows
• Online Control via Counterfactual Tracking
• Asynchronous Replanning in Two Population Linear Quadratic Mean Field Games: Information Requirements and Stability
• Petrov-Galerkin operator inference with application to stability-encouraging identification