Extracting Governing Equations from Latent Dynamics via Multi-View Contrastive Learning

• URL: http://arxiv.org/abs/2606.13260v1
• Date: Thu, 11 Jun 2026 12:16:35 GMT
• Title: Extracting Governing Equations from Latent Dynamics via Multi-View Contrastive Learning
• Abstract summary: 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.
• Score: 1.9754011041953696
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Identifying latent dynamical systems from noisy, high-dimensional measurements is a central problem at the intersection of representation learning, system identification, and scientific discovery. We present DYSCO, a multi-view temporal contrastive learning algorithm that jointly recovers latent trajectories and the governing dynamics from such observations, by leveraging multiple independent noisy views of the same underlying process to disentangle signal from noise. By parameterizing the dynamics in a structured functional basis, our framework further enables symbolic recovery of the governing equations within an affine gauge. We offer theoretical guarantees for strong identification up to an affine indeterminacy, extending prior identifiability results to the realistic setting of noisy nonlinear observations. Empirically, we demonstrate accurate recovery of both latent trajectories and flow fields across a diverse set of dynamical regimes (e.g., chaotic, oscillatory, and metastable) under both Gaussian and Poisson observation noise, the latter being particularly relevant for neural recordings.

Related papers

• Hierarchical Policy Learning via Spectral Decomposition [58.65543693788772]
  We identify a semantic decomposition in robot action sequences, separating task-level motion intent from execution-level refinements.<n>Motivated by this structure, we propose Causal Spectral Policy (CSP), which models action generation as a causal coarse-to-fine process.<n>CSP consistently outperforms strong baselines on precision-sensitive manipulation tasks.
  arXiv  Detail & Related papers  (2026-06-28T19:22:40Z)
• Asymptotic Signal Subspace Recovery in Softmax Attention Models [16.70141872088154]
  We study a stylized softmax-attention model in which a query vector is learned by gradient ascent from a collection of informative and tokens.<n>We show that the learned query converges almost surely to the one-dimensional signal subspace spanned by the latent informative direction.<n>These results provide a rigorous theoretical foundation for understanding attention mechanisms in high-dimensional noisy environments.
  arXiv  Detail & Related papers  (2026-06-21T09:38:59Z)
• A machine learning framework for uncovering stochastic nonlinear dynamics from noisy data [35.634572760830764]
  Noise influences the inference of system parameters and ignore dynamics from data.<n>We develop a hybrid symbolic regression-probabilistic machine learning framework that recovers the symbolic form of the governing equations while simultaneously inferring uncertainty in the system parameters.<n>The framework is data-efficient, requiring as few as 100-1000 data points, and robust to noise - demonstrating its broad potential in domains where uncertainty is intrinsic and both the structure and variability of dynamical systems must be understood.
  arXiv  Detail & Related papers  (2026-04-07T16:59:40Z)
• 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)
• Physics-Guided Dual Implicit Neural Representations for Source Separation [70.38762322922211]
  We develop a self-supervised machine-learning approach for source separation using a dual implicit neural representation framework.<n>Our method learns directly from the raw data by minimizing a reconstruction-based loss function.<n>Our method offers a versatile framework for addressing source separation problems across diverse domains.
  arXiv  Detail & Related papers  (2025-07-07T17:56:31Z)
• Generative System Dynamics in Recurrent Neural Networks [56.958984970518564]
  We investigate the continuous time dynamics of Recurrent Neural Networks (RNNs)<n>We show that skew-symmetric weight matrices are fundamental to enable stable limit cycles in both linear and nonlinear configurations.<n> Numerical simulations showcase how nonlinear activation functions not only maintain limit cycles, but also enhance the numerical stability of the system integration process.
  arXiv  Detail & Related papers  (2025-04-16T10:39:43Z)
• Communities in the Kuramoto Model: Dynamics and Detection via Path Signatures [1.024113475677323]
  We propose the use of path signatures, a mathematical framework that encodes geometric and temporal properties of continuous paths.<n>We propose a novel signature-based community detection algorithm, achieving exact recovery of structural communities from observed time series.<n>Our results demonstrate that path signatures provide a novel perspective on analyzing complex neural data and other high-dimensional systems.
  arXiv  Detail & Related papers  (2025-03-21T21:41:48Z)
• Stochastic action for the entanglement of a noisy monitored two-qubit system [55.2480439325792]
  We study the effect of local unitary noise on the entanglement evolution of a two-qubit system subject to local monitoring and inter-qubit coupling. We construct a Hamiltonian by incorporating the noise into the Chantasri-Dressel-Jordan path integral and use it to identify the optimal entanglement dynamics. Numerical investigation of long-time steady-state entanglement reveals a non-monotonic relationship between concurrence and noise strength.
  arXiv  Detail & Related papers  (2024-03-13T11:14:10Z)
• An Interventional Perspective on Identifiability in Gaussian LTI Systems with Independent Component Analysis [44.892642197610215]
  We show that in Gaussian Linear Time-Invariant (LTI) systems, the system parameters can be identified by introducing diverse intervention signals. We show that Hidden Markov Models, in general, and (Gaussian) LTI systems, fulfil a generalization of the Causal de Finetti theorem with continuous parameters.
  arXiv  Detail & Related papers  (2023-11-29T19:51:35Z)
• Learning invariant representations of time-homogeneous stochastic dynamical systems [27.127773672738535]
  We study the problem of learning a representation of the state that faithfully captures its dynamics. This is instrumental to learning the transfer operator or the generator of the system. We show that the search for a good representation can be cast as an optimization problem over neural networks.
  arXiv  Detail & Related papers  (2023-07-19T11:32:24Z)
• 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)
• Reconstructing a dynamical system and forecasting time series by self-consistent deep learning [4.947248396489835]
  We introduce a self-consistent deep-learning framework for a noisy deterministic time series. It provides unsupervised filtering, state-space reconstruction, identification of the underlying differential equations and forecasting.
  arXiv  Detail & Related papers  (2021-08-04T06:10:58Z)
• Variational Deep Learning for the Identification and Reconstruction of Chaotic and Stochastic Dynamical Systems from Noisy and Partial Observations [15.82296284460491]
  The identification of governing equations remains challenging when dealing with noisy and partial observations. Within the proposed framework, we learn an inference model to reconstruct the true states of the system. This framework bridges classical data assimilation and state-of-the-art machine learning techniques.
  arXiv  Detail & Related papers  (2020-09-04T16:48:00Z)

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.