Limits of Learning Linear Dynamics from Experiments

• URL: http://arxiv.org/abs/2605.12010v1
• Date: Tue, 12 May 2026 12:00:37 GMT
• Title: Limits of Learning Linear Dynamics from Experiments
• Abstract summary: We show that the experimental setup dictates a fundamental limit on the information recoverable from the observed trajectory.<n>We prove that even when the full system is not identifiable, the restricted dynamics on the subspace reachable by the experiment remain uniquely determined.
• Score: 8.916035365052398
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Monitoring Data-aware Temporal Properties (Extended Version) [56.386411908764494]
  We consider anticipatory monitoring of linear-time properties enriched with an arbitrary SMT theory over finite traces.<n>Anticipatory monitoring in this setting is highly challenging, as the monitoring state depends on both the trace prefix seen so far and all its possible finite continuations.<n>We present and formally prove the correctness of a novel foundational framework for monitoring properties in an expressive fragment offMT.
  arXiv  Detail & Related papers  (2026-05-14T10:23:11Z)
• Learning Hidden Structures in Open Quantum Dynamics [78.4675086615913]
  We introduce a machine-learning approach for identifying hidden structural features of open quantum dynamics under restricted experimental access.<n>Our framework targets the inference of invariant algebraic structures underlying the effective Markovian evolution.<n>The feasibility of the approach is illustrated on multiple synthetic models and a waveguide quantum electrodynamics system.
  arXiv  Detail & Related papers  (2026-04-01T10:20:38Z)
• Active Localization of Unstable Systems with Coarse Information [2.094349987888854]
  We study localization and control for unstable systems under coarse, single-bit sensing.<n>We develop an active localization algorithm that integrates a set-based estimator with a control strategy derived from Voronoi partitions.
  arXiv  Detail & Related papers  (2026-02-05T20:56:16Z)
• When is a System Discoverable from Data? Discovery Requires Chaos [36.78844761101327]
  We show that chaos is crucial for ensuring a system is discoverable in the space of continuous or analytic functions.<n>We demonstrate for the first time that the classical Lorenz system is analytically discoverable.<n>These findings help explain the success of data-driven methods in inherently chaotic domains like weather forecasting.
  arXiv  Detail & Related papers  (2025-11-12T00:35:54Z)
• Identifiability Challenges in Sparse Linear Ordinary Differential Equations [4.895067344504143]
  We show that sparse systems are unidentifiable with a positive probability in practically relevant sparsity regimes.<n>We further study empirically how this theoretical unidentifiability manifests in state-of-the-art methods to estimate linear ODEs from data.
  arXiv  Detail & Related papers  (2025-06-11T14:55:36Z)
• Identifiability and Asymptotics in Learning Homogeneous Linear ODE Systems from Discrete Observations [114.17826109037048]
  Ordinary Differential Equations (ODEs) have recently gained a lot of attention in machine learning. theoretical aspects, e.g., identifiability and properties of statistical estimation are still obscure. This paper derives a sufficient condition for the identifiability of homogeneous linear ODE systems from a sequence of equally-spaced error-free observations sampled from a single trajectory.
  arXiv  Detail & Related papers  (2022-10-12T06:46:38Z)
• Sparsity in Partially Controllable Linear Systems [56.142264865866636]
  We study partially controllable linear dynamical systems specified by an underlying sparsity pattern. Our results characterize those state variables which are irrelevant for optimal control.
  arXiv  Detail & Related papers  (2021-10-12T16:41:47Z)
• Unsupervised machine learning of topological phase transitions from experimental data [52.77024349608834]
  We apply unsupervised machine learning techniques to experimental data from ultracold atoms. We obtain the topological phase diagram of the Haldane model in a completely unbiased fashion. Our work provides a benchmark for unsupervised detection of new exotic phases in complex many-body systems.
  arXiv  Detail & Related papers  (2021-01-14T16:38:21Z)
• Deep Learning based Uncertainty Decomposition for Real-time Control [9.067368638784355]
  We propose a novel method for detecting the absence of training data using deep learning. We show its advantages over existing approaches on synthetic and real-world datasets. We further demonstrate the practicality of this uncertainty estimate in deploying online data-efficient control on a simulated quadcopter.
  arXiv  Detail & Related papers  (2020-10-06T10:46:27Z)
• Active Learning for Nonlinear System Identification with Guarantees [102.43355665393067]
  We study a class of nonlinear dynamical systems whose state transitions depend linearly on a known feature embedding of state-action pairs. We propose an active learning approach that achieves this by repeating three steps: trajectory planning, trajectory tracking, and re-estimation of the system from all available data. We show that our method estimates nonlinear dynamical systems at a parametric rate, similar to the statistical rate of standard linear regression.
  arXiv  Detail & Related papers  (2020-06-18T04:54:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.