Deep Spectral Learning of Embedded Latent Transfer Operators for Stochastic Dynamical Systems

• URL: http://arxiv.org/abs/2606.14079v1
• Date: Fri, 12 Jun 2026 03:55:11 GMT
• Title: Deep Spectral Learning of Embedded Latent Transfer Operators for Stochastic Dynamical Systems
• Abstract summary: We instantiate the method as Deep Spectral (DSE), an operator-based latent state-space model.<n>We generalize sequential Bayesian filtering and Koopman spectral mode decomposition in feature space.
• Score: 5.4806374384787695
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose a spectral learning method for stochastic nonlinear dynamical systems represented with embedded latent transfer operators in deep feature spaces. We instantiate the method as Deep Spectral Encoder (DSE), an operator-based latent state-space model in which a time-invariant neural encoder implements learnable nonlinear feature maps from observations, and these features define Markovian latent states whose temporal evolution and observation mapping are described by the transfer and observation operators, respectively. Functional canonical correlation analysis in a learnable Galerkin-projected feature space provides state coordinates from past and future observations, and the two linear operators are estimated on the state coordinates as ridge-regularized closed-form solutions that coincide with Galerkin projections of the associated covariance operators. On this representation, we generalize sequential Bayesian filtering and Koopman spectral mode decomposition in feature space. Experiments on several scenarios show stable and superior performance with sequential Bayesian filtering and dynamic mode decomposition baselines even under noise and partial observability.

Related papers

• Extracting Governing Equations from Latent Dynamics via Multi-View Contrastive Learning [1.9754011041953696]
  We present DYSCO, a multi-view temporal contrastive learning algorithm that jointly recovers latent trajectories and the governing dynamics from such observations.<n>We offer theoretical guarantees for strong identification up to an affine indeterminacy, extending prior identifiability results to the realistic setting of noisy nonlinear observations.
  arXiv  Detail & Related papers  (2026-06-11T12:16:35Z)
• Implicit Neural Representations: A Signal Processing Perspective [54.57279006229212]
  Implicit neural representations (INRs) mark a fundamental shift in signal modeling, moving from discrete sampled data to continuous functional representations.<n>This article examines the evolution of INRs from a signal processing perspective, emphasizing spectral behavior, sampling theory, and multiscale representation.<n>We highlight the utility of INRs across a broad range of applications, including inverse problems in medical and radar imaging, compression, and 3D scene representation.
  arXiv  Detail & Related papers  (2026-04-16T14:12:06Z)
• GeodesicNVS: Probability Density Geodesic Flow Matching for Novel View Synthesis [54.39598154430305]
  We propose a Data-to-Data Flow Matching framework that learns deterministic transformations directly between paired views.<n>PDG-FM constrains flow trajectories using geodesic interpolants derived from probability density metrics of pretrained diffusion models.<n>These results highlight the advantages of incorporating data-dependent geometric regularization into deterministic flow matching for consistent novel view generation.
  arXiv  Detail & Related papers  (2026-03-01T09:30:11Z)
• KoopGen: Koopman Generator Networks for Representing and Predicting Dynamical Systems with Continuous Spectra [65.11254608352982]
  We introduce a generator-based neural Koopman framework that models dynamics through a structured, state-dependent representation of Koopman generators.<n>By exploiting the intrinsic Cartesian decomposition into skew-adjoint and self-adjoint components, KoopGen separates conservative transport from irreversible dissipation.
  arXiv  Detail & Related papers  (2026-02-15T06:32:23Z)
• Echo State Networks as State-Space Models: A Systems Perspective [10.710447183485284]
  We show that the echo-state property is an instance of input-to-state stability for a contractive nonlinear SSM.<n>We also develop two complementary mappings that yield locally valid LTI SSMs with interpretable poles and memory horizons.<n>This perspective yields frequency-domain characterizations of memory spectra and clarifies when ESNs emulate structured SSM kernels.
  arXiv  Detail & Related papers  (2025-09-04T17:42:03Z)
• Learning Stochastic Nonlinear Dynamics with Embedded Latent Transfer Operators [5.074981199059028]
  We consider an operator-based latent Markov representation of a nonlinear dynamical system.<n>The embedding may be learned simultaneously using reproducing kernels, for example, constructed with feed-forward neural networks.<n>We also address the generalization of sequential state-estimation in nonlinear systems, and of operator-based eigen-mode decomposition of dynamics.
  arXiv  Detail & Related papers  (2025-01-06T02:25:48Z)
• Koopman operators with intrinsic observables in rigged reproducing kernel Hilbert spaces [16.00267662259167]
  This paper presents a novel approach for estimating the Koopman operator defined on a reproducing kernel Hilbert space (RKHS) and its spectra. We propose an estimation method, what we call Jet Dynamic Mode Decomposition (JetDMD), leveraging the intrinsic structure of RKHS and the geometric notion known as jets. This method refines the traditional Extended Dynamic Mode Decomposition (EDMD) in accuracy, especially in the numerical estimation of eigenvalues.
  arXiv  Detail & Related papers  (2024-03-04T22:28:20Z)
• Beyond expectations: Residual Dynamic Mode Decomposition and Variance for Stochastic Dynamical Systems [8.259767785187805]
  Dynamic Mode Decomposition (DMD) is the poster child of projection-based methods. We introduce the concept of variance-pseudospectra to gauge statistical coherency. Our study concludes with practical applications using both simulated and experimental data.
  arXiv  Detail & Related papers  (2023-08-21T13:05:12Z)
• Spectral Decomposition Representation for Reinforcement Learning [100.0424588013549]
  We propose an alternative spectral method, Spectral Decomposition Representation (SPEDER), that extracts a state-action abstraction from the dynamics without inducing spurious dependence on the data collection policy. A theoretical analysis establishes the sample efficiency of the proposed algorithm in both the online and offline settings. An experimental investigation demonstrates superior performance over current state-of-the-art algorithms across several benchmarks.
  arXiv  Detail & Related papers  (2022-08-19T19:01:30Z)
• Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings [97.12538243736705]
  We study reinforcement learning with function approximation for large-scale Partially Observable Decision Processes (POMDPs) Our algorithm provably scales to large-scale POMDPs.
  arXiv  Detail & Related papers  (2022-06-24T05:13:35Z)
• Stochastically forced ensemble dynamic mode decomposition for forecasting and analysis of near-periodic systems [65.44033635330604]
  We introduce a novel load forecasting method in which observed dynamics are modeled as a forced linear system. We show that its use of intrinsic linear dynamics offers a number of desirable properties in terms of interpretability and parsimony. Results are presented for a test case using load data from an electrical grid.
  arXiv  Detail & Related papers  (2020-10-08T20:25:52Z)

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.