stat.MLNov 2, 2026

On Stochastic Continuous-Time Linear System Identification for Adaptive Stabilization

Authors: Reza Sadeghi Hafshejani, Mohamad Kazem Shirani Faradonbeh

Organizations: Department of Mathematics, Southern Methodist University, Dallas, TX 75205, USA

Abstract

System identification studies the canonical problem of reliably learning system-dynamics from state and input trajectories. One of its important applications consists of estimating a feedback gain matrix that can stabilize an unknown system. This paper focuses on the analysis of such adaptive stabilization schemes for multivariate linear time-invariant state-space models. The system instability practically renders trajectories short, i.e., the observed data is notably limited. So, it is crucial to tightly consider effects of all involved quantities including length and number of trajectories, dimension, controllability Gramian, and signal-to-noise ratio. We put forward a simple, practical, and reliable relationship between the chance that adaptive stabilization (based on system identification) fails to stabilize the system, in terms of all the above-mentioned quantities. Our findings show that despite exponential effects of all other quantities on failure probability, such effects do not hold for signal-to-noise ratio. More specifically, this study shows that the strength of the excitation signal helps stabilization only logarithmically; a very important phenomenon that we explain under the term signal saturation.

Explore similar work

CardsList
  1. Neural Closed-Loop Identification of Nonlinear Systems with Stability and Generalization Guarantees

    Oct 20, 2026Laura Meroi, Mahrokh G. Boroujeni, Leonardo Massai +1PAC-Bayesian TheoryNonlinear System Identification

  2. Limits of Learning Linear Dynamics from Experiments

    May 12, 2026Aybüke Ulusarslan, Niki Kilbertus, Nora SchneiderDynamical SystemsParameter Identifiability

  3. RobustLDS: Learning linear dynamical systems under adversarial corruptions

    Oct 8, 2026Aravinda Kanchana Ruwanpathirana, Hemant TyagiSystem IdentificationRobust Estimation