Performative Control for Linear Dynamical Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cai, Songfu, Han, Fei, Cao, Xuanyu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909372715630592
author Cai, Songfu
Han, Fei
Cao, Xuanyu
author_facet Cai, Songfu
Han, Fei
Cao, Xuanyu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_23251
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Performative Control for Linear Dynamical Systems
Cai, Songfu
Han, Fei
Cao, Xuanyu
Optimization and Control
Dynamical Systems
93C06 (Primary) 68T06, 37N06 (Secondary)
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.
title Performative Control for Linear Dynamical Systems
topic Optimization and Control
Dynamical Systems
93C06 (Primary) 68T06, 37N06 (Secondary)
url https://arxiv.org/abs/2410.23251