Universal set of Observables for Forecasting Physical Systems through Causal Embedding

• URL: http://arxiv.org/abs/2105.10759v3
• Date: Mon, 3 Apr 2023 20:32:09 GMT
• Title: Universal set of Observables for Forecasting Physical Systems through Causal Embedding
• Authors: G Manjunath, A de Clercq and MJ Steynberg
• Abstract summary: We demonstrate when and how an entire left-infinite orbit of an underlying dynamical system or observations can be uniquely represented by a pair of elements in a different space. The collection of such pairs is derived from a driven dynamical system and is used to learn a function which together with the driven system would: (i.) determine a system that is topologically conjugate to the underlying system.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We demonstrate when and how an entire left-infinite orbit of an underlying dynamical system or observations from such left-infinite orbits can be uniquely represented by a pair of elements in a different space, a phenomenon which we call \textit{causal embedding}. The collection of such pairs is derived from a driven dynamical system and is used to learn a function which together with the driven system would: (i). determine a system that is topologically conjugate to the underlying system (ii). enable forecasting the underlying system's dynamics since the conjugacy is computable and universal, i.e., it does not depend on the underlying system (iii). guarantee an attractor containing the image of the causally embedded object even if there is an error made in learning the function. By accomplishing these we herald a new forecasting scheme that beats the existing reservoir computing schemes that often lead to poor long-term consistency as there is no guarantee of the existence of a learnable function, and overcomes the challenges of stability in Takens delay embedding. We illustrate accurate modeling of underlying systems where previously known techniques have failed.

Related papers

• AI-Lorenz: A physics-data-driven framework for black-box and gray-box identification of chaotic systems with symbolic regression [2.07180164747172]
  We develop a framework that learns mathematical expressions modeling complex dynamical behaviors. We train a small neural network to learn the dynamics of a system, its rate of change in time, and missing model terms. This, in turn, enables us to predict the future evolution of the dynamical behavior.
  arXiv  Detail & Related papers  (2023-12-21T18:58:41Z)
• A Constructive Approach to Function Realization by Neural Stochastic Differential Equations [8.04975023021212]
  We introduce structural restrictions on system dynamics and characterize the class of functions that can be realized by such a system. The systems are implemented as a cascade interconnection of a neural differential equation (Neural SDE), a deterministic dynamical system, and a readout map.
  arXiv  Detail & Related papers  (2023-07-01T03:44:46Z)
• 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)
• 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)
• Supervised DKRC with Images for Offline System Identification [77.34726150561087]
  Modern dynamical systems are becoming increasingly non-linear and complex. There is a need for a framework to model these systems in a compact and comprehensive representation for prediction and control. Our approach learns these basis functions using a supervised learning approach.
  arXiv  Detail & Related papers  (2021-09-06T04:39:06Z)
• Embedding Information onto a Dynamical System [0.0]
  We show how an arbitrary sequence can be mapped into another space as an attractive solution of a nonautonomous dynamical system. This result is not a generalization of Takens embedding theorem but helps us understand what exactly is required by discrete-time state space models.
  arXiv  Detail & Related papers  (2021-05-22T16:54:16Z)
• 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)
• Euclideanizing Flows: Diffeomorphic Reduction for Learning Stable Dynamical Systems [74.80320120264459]
  We present an approach to learn such motions from a limited number of human demonstrations. The complex motions are encoded as rollouts of a stable dynamical system. The efficacy of this approach is demonstrated through validation on an established benchmark as well demonstrations collected on a real-world robotic system.
  arXiv  Detail & Related papers  (2020-05-27T03:51:57Z)
• Data-Driven Verification under Signal Temporal Logic Constraints [0.0]
  We consider systems under uncertainty whose dynamics are partially unknown. Our aim is to study satisfaction of temporal logic properties by trajectories of such systems. We employ Bayesian inference techniques to associate a confidence value to the satisfaction of the property.
  arXiv  Detail & Related papers  (2020-05-08T08:32:30Z)
• 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)
• An information-geometric approach to feature extraction and moment reconstruction in dynamical systems [0.0]
  We show that orbits of a dynamical system induce probability measures over the measurable space defined by (partial) observations of the system. We show that the evolution of the moments of the dynamics-dependent probability measures can be related to a time-averaging operator on the original dynamical system. We present applications to ergodic dynamical systems on the 2-torus and the Lorenz 63 system.
  arXiv  Detail & Related papers  (2020-04-05T12:07:21Z)

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.