Defines a positivity certificate for finite-sample identifiability of the control-channel block in Koopman EDMDc and derives closed-loop statistical bounds under behavior policies.
Dynamic mode decomposition with control
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
The relative root-mean-square error of finite-dimensional Koopman Control Family predictors is strictly upper-bounded by the square root of the largest eigenvalue of the newly defined control forward-backward consistency matrix.
RC-Koopman uses reservoir computing as a stateful Koopman dictionary with spectral radius controlling temporal memory to achieve accurate and stable identification of nonlinear systems.
A framework identifies homogeneous polynomial dynamical systems from data by directly learning low-rank tensor factors via alternating least-squares on tensor train, hierarchical Tucker, and canonical polyadic decompositions.
citing papers explorer
-
Control-Channel Informativity for Koopman EDMDc under Behavior-Policy Data
Defines a positivity certificate for finite-sample identifiability of the control-channel block in Koopman EDMDc and derives closed-loop statistical bounds under behavior policies.
-
Control Forward-Backward Consistency: Quantifying the Accuracy of Koopman Control Family Models
The relative root-mean-square error of finite-dimensional Koopman Control Family predictors is strictly upper-bounded by the square root of the largest eigenvalue of the newly defined control forward-backward consistency matrix.
-
Koopman Identification of Nonlinear Systems via Reservoir Liftings
RC-Koopman uses reservoir computing as a stateful Koopman dictionary with spectral radius controlling temporal memory to achieve accurate and stable identification of nonlinear systems.
-
Data-Driven Tensor Decomposition Identification of Homogeneous Polynomial Dynamical Systems
A framework identifies homogeneous polynomial dynamical systems from data by directly learning low-rank tensor factors via alternating least-squares on tensor train, hierarchical Tucker, and canonical polyadic decompositions.
- Limitations of LTI Koopman Modeling for Nonlinear Control Systems