Finite sample properties of system identification methods

DOI10.1109/TAC.2002.800750MaRDI QIDQ5267113zbMATH OpenFDO

Authors M. C. Campi, Erik Weyer

Publication date 20 June 2017

Published in IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/TAC.2002.800750

Mathematics Subject Classification ID

Identification in stochastic control theory (93E12)

Cited in

(27)

• The size of the membership-set in a probabilistic framework.
• Accuracy of linear multiple-input multiple-output (MIMO) models obtained by maximum likelihood estimation
• Non-asymptotic quality assessment of generalised FIR models with periodic inputs
• Mode identification with finite statistics (Corresp.)
• Online data-enabled predictive control
• From experiment design to closed-loop control
• Gradient descent learns linear dynamical systems
• Low-complexity learning of linear quadratic regulators from noisy data
• On the sample complexity of the linear quadratic regulator
• Active Operator Inference for Learning Low-Dimensional Dynamical-System Models from Noisy Data
• A combined MAP and Bayesian scheme for finite data and/or moving horizon estimation
• Non-asymptotic state-space identification of closed-loop stochastic linear systems using instrumental variables
• Data-dependent analysis of model validation errors for linear system identification
• scientific article; zbMATH DE number 7625185 (Why is no real title available?)
• Finite sample properties of virtual reference feedback tuning control
• Assessing the quality of identified models through the asymptotic theory -- when is the result reliable?
• Identification of linear systems with multiplicative noise from multiple trajectory data
• Non-asymptotic confidence regions for model parameters in the presence of unmodelled dynamics
• Stochastic online optimization for cyber-physical and robotic systems
• Linear RNNs provably learn linear dynamical systems
• Guaranteed non-asymptotic confidence regions in system identification
• Approximability models and optimal system identification
• Non-asymptotic confidence ellipsoids for the least-squares estimate
• A finite-sample generalization bound for stable LPV systems
• Joint learning of linear dynamical systems under smoothness constraints
• scientific article; zbMATH DE number 7370543 (Why is no real title available?)
• Convergence analysis of central and minimax algorithms in scalar regressor models

This page was built for publication: Finite sample properties of system identification methods

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5267113)