Embedding Hybrid Systems into Continuous Latent Vector Fields

• URL: http://arxiv.org/abs/2606.10596v1
• Date: Tue, 09 Jun 2026 09:01:18 GMT
• Title: Embedding Hybrid Systems into Continuous Latent Vector Fields
• Abstract summary: This work proves that an $n$-dimensional hybrid system can be embedded into a $m$-dimensional Euclidean space equipped with a continuous vector field on its embedded image whenever $m>2n$.<n>Building on this existence theorem, we show that a latent Neural ODE with consistency loss in both the latent and state space can accurately recover the flow of hybrid systems.
• Score: 10.094395881446294
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This work proves that an $n$-dimensional hybrid system can be embedded into an $m$-dimensional Euclidean space equipped with a continuous vector field on its embedded image whenever $m>2n$. This result suggests that an intrinsically discontinuous hybrid system generically admits a continuous extrinsic representation that is well-posed for differentiable optimization. Building on this existence theorem, we show that a latent Neural ODE with consistency loss in both the latent and state space can accurately recover the flow of hybrid systems. Extensive experiments suggest the proposed method outperforms the existing method in learning hybrid systems with varying geometries from only time series data.

Related papers

• Intrinsic-Hybrid Latent Diffusion Models for Generative Modeling on Unknown Manifolds [7.1936189117668725]
  Intrinsic Hybrid Latent Diffusion Model (ILDM) is a generative framework that integrates probabilistic dimensionality reduction with geometry-aware diffusion on unknown manifold.<n> experiments on COIL-100, MNIST, and cardiac MRI datasets demonstrate that ILDM significantly improves generation quality.
  arXiv  Detail & Related papers  (2026-08-05T13:28:08Z)
• Nonlocality-induced critical-length hierarchy from non-Hermitian competition [48.9823527611878]
  In short-range systems formed by two coupled chains, competition leads to the critical-length law $N_csimln D$.<n>Here we show that long-range hoppings fundamentally reorganizes this critical behavior, producing a hierarchy of distinct scaling laws.<n>Our results offer a platform-independent framework testable in programmable topoelectrical circuits, photonic lattices and digital quantum simulators.
  arXiv  Detail & Related papers  (2026-08-03T18:00:18Z)
• CHyLL: Learning Continuous Neural Representations of Hybrid Systems [11.771902164764514]
  We propose CHyLL, which learns a continuous neural representation of a hybrid system without trajectory segmentation, event functions, or mode switching.<n>We showcase that CHyLL can accurately predict the flow of hybrid systems with superior accuracy and identify the topological invariants of the hybrid systems.
  arXiv  Detail & Related papers  (2025-12-10T22:07:16Z)
• Enforcing Latent Euclidean Geometry in Single-Cell VAEs for Manifold Interpolation [79.27003481818413]
  We introduce FlatVI, a training framework that regularises the latent manifold of discrete-likelihood variational autoencoders towards Euclidean geometry.<n>By encouraging straight lines in the latent space to approximate geodesics on the decoded single-cell manifold, FlatVI enhances compatibility with downstream approaches.
  arXiv  Detail & Related papers  (2025-07-15T23:08:14Z)
• Linear Convergence of Diffusion Models Under the Manifold Hypothesis [5.040884755454258]
  We show that the number of steps to converge in Kullback-Leibler(KL) divergence is linear (up to logarithmic terms) in the intrinsic dimension $Leid$.<n>We also show that this linear dependency is sharp.
  arXiv  Detail & Related papers  (2024-10-11T17:58:30Z)
• Learning and Concentration for High Dimensional Linear Gaussians: an Invariant Subspace Approach [0.0]
  We study non-asymptotic bounds on correlation between two time realizations of stable linear systems with isotropic Gaussian noise. Our analysis provide first interpretable and geometric explanation into intricacies of learning and concentration for random dynamical systems.
  arXiv  Detail & Related papers  (2023-04-04T11:11:26Z)
• Hybrid discrete-continuous truncated Wigner approximation for driven, dissipative spin systems [0.0]
  We present a systematic approach for the treatment of many-body dynamics of interacting, open spin systems. Our approach overcomes some of the shortcomings of the recently developed discrete truncated Wigner approximation (DTWA) We show that the continuous embedding allows for a straightforward extension of the method to open spin systems subject to dephasing, losses and incoherent drive.
  arXiv  Detail & Related papers  (2022-03-31T15:40:18Z)
• Convex Analysis of the Mean Field Langevin Dynamics [49.66486092259375]
  convergence rate analysis of the mean field Langevin dynamics is presented. $p_q$ associated with the dynamics allows us to develop a convergence theory parallel to classical results in convex optimization.
  arXiv  Detail & Related papers  (2022-01-25T17:13:56Z)
• Non-Hermitian $C_{NH} = 2$ Chern insulator protected by generalized rotational symmetry [85.36456486475119]
  A non-Hermitian system is protected by the generalized rotational symmetry $H+=UHU+$ of the system. Our finding paves the way towards novel non-Hermitian topological systems characterized by large values of topological invariants.
  arXiv  Detail & Related papers  (2021-11-24T15:50:22Z)
• Exact solutions of interacting dissipative systems via weak symmetries [77.34726150561087]
  We analytically diagonalize the Liouvillian of a class Markovian dissipative systems with arbitrary strong interactions or nonlinearity. This enables an exact description of the full dynamics and dissipative spectrum. Our method is applicable to a variety of other systems, and could provide a powerful new tool for the study of complex driven-dissipative quantum systems.
  arXiv  Detail & Related papers  (2021-09-27T17:45:42Z)
• Lifting the Convex Conjugate in Lagrangian Relaxations: A Tractable Approach for Continuous Markov Random Fields [53.31927549039624]
  We show that a piecewise discretization preserves better contrast from existing discretization problems. We apply this theory to the problem of matching two images.
  arXiv  Detail & Related papers  (2021-07-13T12:31:06Z)
• Identification of Probability weighted ARX models with arbitrary domains [75.91002178647165]
  PieceWise Affine models guarantees universal approximation, local linearity and equivalence to other classes of hybrid system. In this work, we focus on the identification of PieceWise Auto Regressive with eXogenous input models with arbitrary regions (NPWARX) The architecture is conceived following the Mixture of Expert concept, developed within the machine learning field.
  arXiv  Detail & Related papers  (2020-09-29T12:50:33Z)

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.