First Order Methods For Globally Optimal Distributed Controllers Beyond Quadratic Invariance

Abstract

We study the distributed Linear Quadratic Gaussian (LQG) control problem in discrete-time and finite-horizon, where the controller depends linearly on the history of the outputs and it is required to lie in a given subspace, e.g. to possess a certain sparsity pattern. It is well-known that this problem can be solved with convex programming within the Youla domain if and only if a condition known as Quadratic Invariance (QI) holds. In this paper, we first show that given QI sparsity constraints, one can directly descend the gradient of the cost function within the domain of output-feedback controllers and converge to a global optimum. Note that convergence is guaranteed despite non-convexity of the cost function. Second, we characterize a class of Uniquely Stationary (US) problems, for which first-order methods are guaranteed to converge to a global optimum. We show that the class of US problems is strictly larger than that of strongly QI problems and that it is not included in that of QI problems. We refer to Figure 1 for details. Finally, we propose a tractable test for the US property.

References in corpus (2)

• LQR through the Lens of First Order Methods: Discrete-time Case
• First Order Methods For Globally Optimal Distributed Controllers Beyond Quadratic Invariance

Cited by in corpus (7)

• Learning the Globally Optimal Distributed LQ Regulator
• First Order Methods For Globally Optimal Distributed Controllers Beyond Quadratic Invariance
• Learning to Boost the Performance of Stable Nonlinear Systems
• Distributed Control-Estimation Synthesis for Stochastic Multi-Agent Systems via Virtual Interaction between Non-neighboring Agents
• Distributed Online Linear Quadratic Control for Linear Time-invariant Systems
• Regret Analysis of Distributed Online LQR Control for Unknown LTI Systems
• On Linear Quadratic Potential Games