Finite sample properties of system identification methods
From MaRDI portal
Publication:5267113
DOI10.1109/TAC.2002.800750zbMath1364.93823MaRDI QIDQ5267113
Publication date: 20 June 2017
Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)
Related Items
Convergence analysis of central and minimax algorithms in scalar regressor models, Non-asymptotic confidence ellipsoids for the least-squares estimate, Online data-enabled predictive control, Data-dependent analysis of model validation errors for linear system identification, Identification of linear systems with multiplicative noise from multiple trajectory data, Active Operator Inference for Learning Low-Dimensional Dynamical-System Models from Noisy Data, Unnamed Item, On the sample complexity of the linear quadratic regulator, Non-asymptotic state-space identification of closed-loop stochastic linear systems using instrumental variables, Accuracy of linear multiple-input multiple-output (MIMO) models obtained by maximum likelihood estimation, A combined MAP and Bayesian scheme for finite data and/or moving horizon estimation, The size of the membership-set in a probabilistic framework., Unnamed Item, Gradient Descent Learns Linear Dynamical Systems, Assessing the quality of identified models through the asymptotic theory -- when is the result reliable?, Non-asymptotic quality assessment of generalised FIR models with periodic inputs, From experiment design to closed-loop control, Low-complexity learning of linear quadratic regulators from noisy data, Finite sample properties of virtual reference feedback tuning control, Approximability models and optimal system identification, Non-asymptotic confidence regions for model parameters in the presence of unmodelled dynamics, Guaranteed non-asymptotic confidence regions in system identification
