Learning Ergodic Dynamical Systems from a Finite Trajectory

• URL: http://arxiv.org/abs/2607.22399v1
• Date: Fri, 24 Jul 2026 15:21:51 GMT
• Title: Learning Ergodic Dynamical Systems from a Finite Trajectory
• Abstract summary: We study discrete-time autonomous systems defining time-homogeneous Markov processes.<n>We first focus on estimating the optimal one-step prediction function by nonlinear least squares.<n>We extend the framework to higher-order systems and finite-state spaces.
• Score: 10.59816347247158
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We consider the problem of learning from a single finite trajectory of an ergodic stochastic dynamical system. More precisely, we study discrete-time autonomous stochastic systems defining time-homogeneous Markov processes. We first focus on estimating the optimal one-step prediction function by nonlinear least squares, and derive high-probability guarantees measured with respect to the invariant measure of the process. These results make explicit how the non-independent and non-identically distributed nature of trajectory data modifies the classical statistical learning analysis. We then extend the framework to higher-order systems and finite-state spaces. Finally, we show that the same least squares and concentration arguments naturally extend to learning Koopman operators. Our approach combines tools from statistical learning theory and quantitative ergodic theory for Markov chains. It relies, in particular, on a concentration inequality for Hilbert-space-valued additive functionals of uniformly geometrically ergodic Markov chains.

Related papers

• Exact Finite-Dimensional Evaluation of Homodyne Quantum Trajectories for Single-Quadrature Hamiltonian [0.0]
  We identify an exactly solvable class of continuously monitored systems.<n>We derive an exact finite-angle representation of the conditional dynamics for arbitrary finite-order quadrature moments.<n>The resulting equations depend only on the Hamiltonian degree and moment order, with computational complexity independent of the Hilbert-space dimension.
  arXiv  Detail & Related papers  (2026-07-28T00:32:22Z)
• Universal Learning of Stochastic Dynamics for Exact Belief Propagation using Bernstein Normalizing Flows [10.143540866021542]
  This paper establishes the theoretical foundations for a class of models that satisfy both properties.<n>The proposed approach combines the expressiveness of normalizing density estimation with the analytical tractability of Bernsteins flows.
  arXiv  Detail & Related papers  (2025-09-19T02:36:35Z)
• Uncertainty quantification for Markov chain induced martingales with application to temporal difference learning [55.197497603087065]
  We analyze the performance of the Temporal Difference (TD) learning algorithm with linear function approximations.<n>We establish novel and general high-dimensional concentration inequalities and Berry-Esseen bounds for vector-valued martingales induced by Markov chains.
  arXiv  Detail & Related papers  (2025-02-19T15:33:55Z)
• Learning Controlled Stochastic Differential Equations [61.82896036131116]
  This work proposes a novel method for estimating both drift and diffusion coefficients of continuous, multidimensional, nonlinear controlled differential equations with non-uniform diffusion. We provide strong theoretical guarantees, including finite-sample bounds for (L2), (Linfty), and risk metrics, with learning rates adaptive to coefficients' regularity. Our method is available as an open-source Python library.
  arXiv  Detail & Related papers  (2024-11-04T11:09:58Z)
• On the Effect of Instability on Learning Continuous-Time Linear Control Systems [0.0]
  We study the problem of system identification for continuous-time dynamics, based on a single finite-length state trajectory.<n>We present a method for estimating the possibly unstable open-loop matrix by employing properly randomized control inputs.<n>We establish theoretical performance guarantees showing that the estimation error decays with trajectory length, a measure of excitability, and the signal-to-noise ratio.
  arXiv  Detail & Related papers  (2024-09-17T16:24:51Z)
• A Dynamical System View of Langevin-Based Non-Convex Sampling [44.002384711340966]
  Non- sampling is a key challenge in machine learning, central to non-rate optimization in deep learning as well as to approximate its significance. Existing guarantees typically only hold for the averaged distances rather than the more desirable last-rate iterates. We develop a new framework that lifts the above issues by harnessing several tools from the theory systems.
  arXiv  Detail & Related papers  (2022-10-25T09:43:36Z)
• Structure-Preserving Learning Using Gaussian Processes and Variational Integrators [62.31425348954686]
  We propose the combination of a variational integrator for the nominal dynamics of a mechanical system and learning residual dynamics with Gaussian process regression. We extend our approach to systems with known kinematic constraints and provide formal bounds on the prediction uncertainty.
  arXiv  Detail & Related papers  (2021-12-10T11:09:29Z)
• Finite-Time Convergence Rates of Nonlinear Two-Time-Scale Stochastic Approximation under Markovian Noise [2.0305676256390934]
  We study the so-called two-time-scale approximation, a simulation-based approach for finding the roots of two coupled nonlinear operators. In particular, we consider the scenario where the data in the method are generated by Markov processes, therefore, they are dependent. Under some fairly standard assumptions on the operators and the Markov processes, we provide a formula that characterizes the convergence rate of the mean square errors generated by the method to zero.
  arXiv  Detail & Related papers  (2021-04-04T15:19:19Z)
• Nonlinear Independent Component Analysis for Continuous-Time Signals [85.59763606620938]
  We study the classical problem of recovering a multidimensional source process from observations of mixtures of this process. We show that this recovery is possible for many popular models of processes (up to order and monotone scaling of their coordinates) if the mixture is given by a sufficiently differentiable, invertible function.
  arXiv  Detail & Related papers  (2021-02-04T20:28:44Z)
• Multiplicative noise and heavy tails in stochastic optimization [62.993432503309485]
  empirical optimization is central to modern machine learning, but its role in its success is still unclear. We show that it commonly arises in parameters of discrete multiplicative noise due to variance. A detailed analysis is conducted in which we describe on key factors, including recent step size, and data, all exhibit similar results on state-of-the-art neural network models.
  arXiv  Detail & Related papers  (2020-06-11T09:58:01Z)
• On dissipative symplectic integration with applications to gradient-based optimization [77.34726150561087]
  We propose a geometric framework in which discretizations can be realized systematically. We show that a generalization of symplectic to nonconservative and in particular dissipative Hamiltonian systems is able to preserve rates of convergence up to a controlled error.
  arXiv  Detail & Related papers  (2020-04-15T00:36:49Z)

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.