English

Performative Control for Linear Dynamical Systems

Optimization and Control 2024-10-31 v1 Dynamical Systems

Abstract

We introduce the framework of performative control, where the policy chosen by the controller affects the underlying dynamics of the control system. This results in a sequence of policy-dependent system state data with policy-dependent temporal correlations. Following the recent literature on performative prediction [21], we introduce the concept of a performatively stable control (PSC) solution. We first propose a sufficient condition for the performative control problem to admit a unique PSC solution with a problem-specific structure of distributional sensitivity propagation and aggregation. We further analyze the impacts of system stability on the existence of the PSC solution. Specifically, for almost surely strongly stable policy-dependent dynamics, the PSC solution exists if the sum of the distributional sensitivities is small enough. However, for almost surely unstable policy-dependent dynamics, the existence of the PSC solution will necessitate a temporally backward decaying of the distributional sensitivities. We finally provide a repeated stochastic gradient descent scheme that converges to the PSC solution and analyze its non-asymptotic convergence rate. Numerical results validate our theoretical analysis.

Keywords

Cite

@article{arxiv.2410.23251,
  title  = {Performative Control for Linear Dynamical Systems},
  author = {Songfu Cai and Fei Han and Xuanyu Cao},
  journal= {arXiv preprint arXiv:2410.23251},
  year   = {2024}
}

Comments

34 pages, 2 figures, NeurIPS 2024

R2 v1 2026-06-28T19:41:45.103Z