Limits of Learning Linear Dynamics from Experiments
Learning governing dynamics from data is a common goal across the sciences, yet it is only well-posed when the underlying mechanisms are identifiable. In practice, many data-driven methods implicitly assume identifiability; when this assumption fails, estimated models can yield spurious predictions and invalid mechanistic conclusions. Classical identifiability guarantees for controlled linear time-invariant (LTI) systems provide sufficient conditions -- controllability and persistent excitation -- but leave open whether identifiability holds when these conditions fail, and which parts of the system remain identifiable without full identifiability. We show that the experimental setup, i.e., the realized initial state and control input, dictates a fundamental limit on the information recoverable from the observed trajectory. We develop a geometric characterization of this limit and derive a closed-form description of all systems consistent with the experimental setup. Crucially, we prove that even when the full system is not identifiable, the restricted dynamics on the subspace reachable by the experiment remain uniquely determined.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Speed Limits for Deep Learning
State-of-the-art neural networks require extreme computational power to train. It is therefore natural to wonder whether they are optimally trained. Here we apply a recent advancement in stochastic thermodynamics which a…
Deep LearningChance-Constrained Trajectory Optimization for Non-linear Systems with Unknown Stochastic Dynamics
Iterative trajectory optimization techniques for non-linear dynamical systems are among the most powerful and sample-efficient methods of model-based reinforcement learning and approximate optimal control. By leveraging …
Model-based Reinforcement LearningSymbolic relative entropy in quantifying nonlinear dynamics of equalities-involved heartbeats
Symbolic relative entropy, an efficient nonlinear complexity parameter measuring probabilistic divergences of symbolic sequences, is proposed in our nonlinear dynamics analysis of heart rates considering equal states. Eq…
Full-Dynamics Real-Time Nonlinear Model Predictive Control of Heavy-Duty Hydraulic Manipulator for Trajectory Tracking Tasks
Heavy-duty hydraulic manipulators (HHMs) operate under strict physical and safety-critical constraints due to their large size, high power, and complex nonlinear dynamics. Ensuring that both joint-level and end-effector …
Disentangling feature and lazy training in deep neural networks
Two distinct limits for deep learning have been derived as the network width $h\rightarrow \infty$, depending on how the weights of the last layer scale with $h$. In the Neural Tangent Kernel (NTK) limit, the dynamics be…