Recovering Governing Equations from Solution Data: Identifiability Bounds for Linear and Nonlinear ODEs

• URL: http://arxiv.org/abs/2606.27285v2
• Date: Fri, 26 Jun 2026 12:45:10 GMT
• Title: Recovering Governing Equations from Solution Data: Identifiability Bounds for Linear and Nonlinear ODEs
• Abstract summary: We introduce the Hausdorff distance on solution sets as the natural metric for comparing differential equations.<n>We establish identifiability bounds for governing ODEs across a wide class of structure equations.<n>We derive metric entropy estimates for the relevant ODE classes and analyze sample complexity bounds.
• Score: 1.360738859820932
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning governing equations from observed solution data is a fundamental challenge in scientific machine learning, yet the theoretical conditions under which a ground-truth ODE can be uniquely and stably identified from multiple solution observations remain largely undeveloped, and no quantitative analysis of the sample complexity of such learning tasks exists in the literature. To address this gap, we introduce the Hausdorff distance on solution sets as the natural metric for comparing differential equations, since it captures the worst-case separation between two equations over all admissible initial conditions and thus encodes the minimax structure of the identification problem. We establish identifiability bounds for governing ODEs across a wide class of structure equations--ranging from linear ODEs to nonlinear classes with Lipschitz (Hölder)-continuous vector fields--characterizing precisely when two distinct equations can be distinguished from solution data. Using this metric, we derive metric entropy estimates for the relevant ODE classes and analyze sample complexity bounds, quantifying how many solution observations are needed to reliably recover the governing equation.

Related papers

• Governing Equation Discovery from Data Based on Differential Invariants [52.2614860099811]
  We propose a pipeline for governing equation discovery based on differential invariants.<n>Specifically, we compute the set of differential invariants corresponding to the infinitesimal generators of the symmetry group.<n>Taking DI-SINDy as an example, we demonstrate that its success rate and accuracy in PDE discovery surpass those of other symmetry-informed governing equation discovery methods.
  arXiv  Detail & Related papers  (2025-05-24T17:19:02Z)
• Data-Driven, ML-assisted Approaches to Problem Well-Posedness [10.544250336831595]
  We show how standard tools from machine and manifold learning can be used to infer, in a data driven manner, certain well-posedness features of differential equation problems.<n>Our study naturally combines a data assimilation perspective with an operator-learning one.
  arXiv  Detail & Related papers  (2025-03-25T01:34:48Z)
• Neuro-Symbolic AI for Analytical Solutions of Differential Equations [14.119864056633434]
  We present an approach to find analytical solutions of differential equations using a neuro-symbolic AI framework.<n>This integration unifies numerical and symbolic differential equation solvers via a neuro-symbolic AI framework.<n>We show advantages over commercial solvers, symbolic methods, and approximate neural networks on a diverse set of problems.
  arXiv  Detail & Related papers  (2025-02-03T16:06:56Z)
• Symbolic Recovery of Differential Equations: The Identifiability Problem [52.158782751264205]
  Symbolic recovery of differential equations is the ambitious attempt at automating the derivation of governing equations. We provide both necessary and sufficient conditions for a function to uniquely determine the corresponding differential equation. We then use our results to devise numerical algorithms aiming to determine whether a function solves a differential equation uniquely.
  arXiv  Detail & Related papers  (2022-10-15T17:32:49Z)
• Tunable Complexity Benchmarks for Evaluating Physics-Informed Neural Networks on Coupled Ordinary Differential Equations [64.78260098263489]
  In this work, we assess the ability of physics-informed neural networks (PINNs) to solve increasingly-complex coupled ordinary differential equations (ODEs) We show that PINNs eventually fail to produce correct solutions to these benchmarks as their complexity increases. We identify several reasons why this may be the case, including insufficient network capacity, poor conditioning of the ODEs, and high local curvature, as measured by the Laplacian of the PINN loss.
  arXiv  Detail & Related papers  (2022-10-14T15:01:32Z)
• 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)
• Constraining Gaussian Processes to Systems of Linear Ordinary Differential Equations [5.33024001730262]
  LODE-GPs follow a system of linear homogeneous ODEs with constant coefficients. We show the effectiveness of LODE-GPs in a number of experiments.
  arXiv  Detail & Related papers  (2022-08-26T09:16:53Z)
• Learning nonparametric ordinary differential equations from noisy data [0.10555513406636088]
  Learning nonparametric systems of Ordinary Differential Equations (ODEs) dot x = f(t,x) from noisy data is an emerging machine learning topic. We use the theory of Reproducing Kernel Hilbert Spaces (RKHS) to define candidates for f for which the solution of the ODE exists and is unique. We propose a penalty method that iteratively uses the Representer theorem and Euler approximations to provide a numerical solution.
  arXiv  Detail & Related papers  (2022-06-30T11:59:40Z)
• D-CIPHER: Discovery of Closed-form Partial Differential Equations [80.46395274587098]
  We propose D-CIPHER, which is robust to measurement artifacts and can uncover a new and very general class of differential equations. We further design a novel optimization procedure, CoLLie, to help D-CIPHER search through this class efficiently.
  arXiv  Detail & Related papers  (2022-06-21T17:59:20Z)
• Feature Engineering with Regularity Structures [4.082216579462797]
  We investigate the use of models from the theory of regularity structures as features in machine learning tasks. We provide a flexible definition of a model feature vector associated to a space-time signal, along with two algorithms which illustrate ways in which these features can be combined with linear regression. We apply these algorithms in several numerical experiments designed to learn solutions to PDEs with a given forcing and boundary data.
  arXiv  Detail & Related papers  (2021-08-12T17:53:47Z)
• Optimal oracle inequalities for solving projected fixed-point equations [53.31620399640334]
  We study methods that use a collection of random observations to compute approximate solutions by searching over a known low-dimensional subspace of the Hilbert space. We show how our results precisely characterize the error of a class of temporal difference learning methods for the policy evaluation problem with linear function approximation.
  arXiv  Detail & Related papers  (2020-12-09T20:19:32Z)
• Solving Differential Equations Using Neural Network Solution Bundles [1.2891210250935146]
  We propose a neural network be used as a solution bundle, a collection of solutions to an ODE for various initial states and system parameters. The solution bundle exhibits fast, parallelizable evaluation of the system state, facilitating the use of Bayesian inference for parameter estimation.
  arXiv  Detail & Related papers  (2020-06-17T02:44:10Z)
• Multipole Graph Neural Operator for Parametric Partial Differential Equations [57.90284928158383]
  One of the main challenges in using deep learning-based methods for simulating physical systems is formulating physics-based data. We propose a novel multi-level graph neural network framework that captures interaction at all ranges with only linear complexity. Experiments confirm our multi-graph network learns discretization-invariant solution operators to PDEs and can be evaluated in linear time.
  arXiv  Detail & Related papers  (2020-06-16T21:56:22Z)

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.