ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2307.03590
18
0

Accelerated Optimization Landscape of Linear-Quadratic Regulator

7 July 2023
Le Feng
Yuan‐Hua Ni
ArXivPDFHTML
Abstract

Linear-quadratic regulator (LQR) is a landmark problem in the field of optimal control, which is the concern of this paper. Generally, LQR is classified into state-feedback LQR (SLQR) and output-feedback LQR (OLQR) based on whether the full state is obtained. It has been suggested in existing literature that both SLQR and OLQR could be viewed as \textit{constrained nonconvex matrix optimization} problems in which the only variable to be optimized is the feedback gain matrix. In this paper, we introduce a first-order accelerated optimization framework of handling the LQR problem, and give its convergence analysis for the cases of SLQR and OLQR, respectively. Specifically, a Lipschiz Hessian property of LQR performance criterion is presented, which turns out to be a crucial property for the application of modern optimization techniques. For the SLQR problem, a continuous-time hybrid dynamic system is introduced, whose solution trajectory is shown to converge exponentially to the optimal feedback gain with Nesterov-optimal order 1−1κ1-\frac{1}{\sqrt{\kappa}}1−κ​1​ (κ\kappaκ the condition number). Then, the symplectic Euler scheme is utilized to discretize the hybrid dynamic system, and a Nesterov-type method with a restarting rule is proposed that preserves the continuous-time convergence rate, i.e., the discretized algorithm admits the Nesterov-optimal convergence order. For the OLQR problem, a Hessian-free accelerated framework is proposed, which is a two-procedure method consisting of semiconvex function optimization and negative curvature exploitation. In a time O(ϵ−7/4log⁡(1/ϵ))\mathcal{O}(\epsilon^{-7/4}\log(1/\epsilon))O(ϵ−7/4log(1/ϵ)), the method can find an ϵ\epsilonϵ-stationary point of the performance criterion; this entails that the method improves upon the O(ϵ−2)\mathcal{O}(\epsilon^{-2})O(ϵ−2) complexity of vanilla gradient descent. Moreover, our method provides the second-order guarantee of stationary point.

View on arXiv
Comments on this paper