On the sample complexity of stabilizing linear dynamical systems from data

DOI10.1007/S10208-023-09605-YzbMATH Open1542.65188MaRDI QIDQ6566152FDOQ6566152

Authors: Steffen W. R. Werner, Benjamin Peherstorfer 

Publication date: 3 July 2024

Published in: Foundations of Computational Mathematics (Search for Journal in Brave)

Recommendations

• Low-complexity learning of linear quadratic regulators from noisy data
• On data-driven stabilization of systems with nonlinearities satisfying quadratic constraints
• System stabilization with policy optimization on unstable latent manifolds
• Data-driven nonlinear stabilization using Koopman operator
• Data-driven stabilization of switched and constrained linear systems

zbMATH Keywords

dynamical systemsmodel reductionnumerical linear algebradata-driven controldata-driven modelingscientific machine learning

Mathematics Subject Classification ID

Feedback control (93B52) Sampled-data control/observation systems (93C57) Stabilization of systems by feedback (93D15) Numerical problems in dynamical systems (65P99) Numerical methods for low-rank matrix approximation; matrix compression (65F55)

Cites Work

• Using SeDuMi 1.02, A Matlab toolbox for optimization over symmetric cones
• Linear Matrix Inequalities in System and Control Theory
• Title not available (Why is that?)
• Title not available (Why is that?)
• Discovering governing equations from data by sparse identification of nonlinear dynamical systems
• Dynamic mode decomposition of numerical and experimental data
• Sparse dynamics for partial differential equations
• Graph implementations for nonsmooth convex programs
• Approximation of Large-Scale Dynamical Systems
• A survey of projection-based model reduction methods for parametric dynamical systems
• Title not available (Why is that?)
• Numerical solution of large-scale Lyapunov equations, Riccati equations, and linear-quadratic optimal control problems.
• A note on persistency of excitation
• Title not available (Why is that?)
• Title not available (Why is that?)
• Virtual reference feedback tuning: A direct method for the design of feedback controllers
• On dynamic mode decomposition: theory and applications
• A new set of invariants for linear systems--Application to reduced order compensator design
• Data-driven interpolation of dynamical systems with delay
• A framework for the solution of the generalized realization problem
• Reduced order methods for modeling and computational reduction
• Title not available (Why is that?)
• Model-free control
• Identification and the Information Matrix: How to Get Just Sufficiently Rich?
• Title not available (Why is that?)
• Title not available (Why is that?)
• A stabilization algorithm for linear discrete constant systems
• An extension of Bass' algorithm for stabilizing linear continuous constant systems
• Parallel partial stabilizing algorithms for large linear control systems
• Data-driven operator inference for nonintrusive projection-based model reduction
• On linear-quadratic optimal control and robustness of differential-algebraic systems
• Data-driven science and engineering. Machine learning, dynamical systems, and control
• Data-driven structured realization
• Formulas for Data-Driven Control: Stabilization, Optimality, and Robustness
• Data Informativity: A New Perspective on Data-Driven Analysis and Control
• System- and Data-Driven Methods and Algorithms
• Data-driven reduced model construction with time-domain Loewner models
• Extracting Sparse High-Dimensional Dynamics from Limited Data
• Sparse identification of nonlinear dynamics for model predictive control in the low-data limit
• On the sample complexity of the linear quadratic regulator
• Data Driven Modal Decompositions: Analysis and Enhancements
• Sampling Low-Dimensional Markovian Dynamics for Preasymptotically Recovering Reduced Models from Data with Operator Inference
• Snapshot-Based Methods and Algorithms
• Robust output-feedback stabilization for incompressible flows using low-dimensional \(\mathcal{H}_{\infty}\)-controllers
• MORLAB -- the model order reduction laboratory
• Multifidelity Monte Carlo Estimation with Adaptive Low-Fidelity Models
• Error bounds for port-Hamiltonian model and controller reduction based on system balancing
• Feedback control for systems with uncertain parameters using online-adaptive reduced models
• Data-driven balancing of linear dynamical systems

Cited In (3)

• Dissipative imitation learning for discrete dynamic output feedback control with sparse data sets
• Design of input assignment and feedback gain for re‐stabilizing undirected networks with High‐Dimension Low‐Sample‐Size data
• System stabilization with policy optimization on unstable latent manifolds

This page was built for publication: On the sample complexity of stabilizing linear dynamical systems from data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6566152)