Metriplectic Conditional Flow Matching for Dissipative Dynamics

• URL: http://arxiv.org/abs/2509.19526v1
• Date: Tue, 23 Sep 2025 19:46:54 GMT
• Title: Metriplectic Conditional Flow Matching for Dissipative Dynamics
• Authors: Ali Baheri, Lars Lindemann,
• Abstract summary: conditional flow matching learns dissipative dynamics without violating first principles.<n>MCFM trains via conditional flow matching on short transitions, avoiding long rollout adjoints.<n>We provide continuous and discrete time guarantees linking this parameterization and sampler to conservation, monotonic dissipation, and stable rollouts.
• Score: 5.920407670799846
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Metriplectic conditional flow matching (MCFM) learns dissipative dynamics without violating first principles. Neural surrogates often inject energy and destabilize long-horizon rollouts; MCFM instead builds the conservative-dissipative split into both the vector field and a structure preserving sampler. MCFM trains via conditional flow matching on short transitions, avoiding long rollout adjoints. In inference, a Strang-prox scheme alternates a symplectic update with a proximal metric step, ensuring discrete energy decay; an optional projection enforces strict decay when a trusted energy is available. We provide continuous and discrete time guarantees linking this parameterization and sampler to conservation, monotonic dissipation, and stable rollouts. On a controlled mechanical benchmark, MCFM yields phase portraits closer to ground truth and markedly fewer energy-increase and positive energy rate events than an equally expressive unconstrained neural flow, while matching terminal distributional fit.

Related papers

• Entropy-Controlled Flow Matching [0.08460698440162889]
  We propose a constrained variational principle over continuity-equation paths enforcing a global entropy-rate budget d/dt H(mu_t) >= -lambda.<n>We obtain certificate-style mode-coverage and density-floor guarantees with Lipschitz, and construct near-optimal counterexamples for unconstrained flow matching.
  arXiv  Detail & Related papers  (2026-02-25T06:07:01Z)
• 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)
• Manifold-Constrained Energy-Based Transition Models for Offline Reinforcement Learning [13.92596311376194]
  We train conditional energy-based transition models using a manifold projection--diffusion negative sampler.<n>MC-ETM learns a latent manifold of next states and generates near-manifold hard negatives.<n>We formalize MC-ETM through a hybrid pessimistic MDP formulation and derive a conservative performance bound separating in-support evaluation error from truncation risk.
  arXiv  Detail & Related papers  (2026-02-02T23:15:43Z)
• Energy-Guided Flow Matching Enables Few-Step Conformer Generation and Ground-State Identification [45.52894539097255]
  We present EnFlow, a unified framework that couples flow matching with an explicitly learned energy model.<n>By incorporating energy-gradient guidance during sampling, our method steers trajectories toward lower-energy regions.<n>The learned energy function further enables efficient energy-based ranking of generated ensembles for accurate ground-state identification.
  arXiv  Detail & Related papers  (2025-12-27T14:00:22Z)
• Particle Dynamics for Latent-Variable Energy-Based Models [12.84928511163926]
  Latent-variable energy-based models (LVEBMs) assign a single normalized energy to joint pairs of observed data and latent variables.<n>We recast maximum-likelihood training as a saddle problem over distributions on the latent and joint gradients.<n>We prove existence and convergence under standard smoothness and dissipativity assumptions, with decay rates in KL divergence and Wasserstein-2 distance.
  arXiv  Detail & Related papers  (2025-10-17T09:04:49Z)
• The Information Dynamics of Generative Diffusion [12.52425103385255]
  Generative diffusion models have emerged as a powerful class of models in machine learning.<n>This paper provides an integrated perspective on generative diffusion by connecting their dynamic, information-theoretic, and thermodynamic properties.
  arXiv  Detail & Related papers  (2025-08-27T13:53:56Z)
• Weighted Conditional Flow Matching [26.88652399504886]
  Conditional flow matching (CFM) has emerged as a powerful framework for training continuous normalizing flows.<n>We propose weighted Conditional Flow Matching (W-CFM), a novel approach that modifies the classical CFM loss by weighting each training pair $(x, y)$ with a Gibbs kernel.
  arXiv  Detail & Related papers  (2025-07-29T22:42:51Z)
• Scalable Equilibrium Sampling with Sequential Boltzmann Generators [60.00515282300297]
  We extend the Boltzmann generator framework with two key contributions.<n>The first is a highly efficient Transformer-based normalizing flow operating directly on all-atom Cartesian coordinates.<n>In particular, we perform inference-time scaling of flow samples using a continuous-time variant of sequential Monte Carlo.
  arXiv  Detail & Related papers  (2025-02-25T18:59:13Z)
• Machine learning in and out of equilibrium [58.88325379746631]
  Our study uses a Fokker-Planck approach, adapted from statistical physics, to explore these parallels. We focus in particular on the stationary state of the system in the long-time limit, which in conventional SGD is out of equilibrium. We propose a new variation of Langevin dynamics (SGLD) that harnesses without replacement minibatching.
  arXiv  Detail & Related papers  (2023-06-06T09:12:49Z)
• Photoinduced prethermal order parameter dynamics in the two-dimensional large-$N$ Hubbard-Heisenberg model [77.34726150561087]
  We study the microscopic dynamics of competing ordered phases in a two-dimensional correlated electron model. We simulate the light-induced transition between two competing phases.
  arXiv  Detail & Related papers  (2022-05-13T13:13:31Z)
• Noise-resilient Edge Modes on a Chain of Superconducting Qubits [103.93329374521808]
  Inherent symmetry of a quantum system may protect its otherwise fragile states. We implement the one-dimensional kicked Ising model which exhibits non-local Majorana edge modes (MEMs) with $mathbbZ$ parity symmetry. MEMs are found to be resilient against certain symmetry-breaking noise owing to a prethermalization mechanism.
  arXiv  Detail & Related papers  (2022-04-24T22:34:15Z)
• Localization transition induced by programmable disorder [0.24629531282150877]
  Many-body localization occurs on a spin-1/2 transverse-field Ising model. We observe a transition from an ergodic phase to a non-thermal phase for individual energy eigenstates. We realize the time-independent disordered Ising Hamiltonian experimentally on a D-Wave 2000Q programmable quantum annealer.
  arXiv  Detail & Related papers  (2021-08-15T15:37:32Z)
• Exceptional Dynamical Quantum Phase Transitions in Periodically Driven Systems [0.0]
  We show that spontaneous symmetry breaking can occur at a short-time regime. Our results open up research for hitherto unknown phases in short-time regimes.
  arXiv  Detail & Related papers  (2020-12-22T04:04:56Z)
• Feedback-induced instabilities and dynamics in the Jaynes-Cummings model [62.997667081978825]
  We investigate the coherence and steady-state properties of the Jaynes-Cummings model subjected to time-delayed coherent feedback. The introduced feedback qualitatively modifies the dynamical response and steady-state quantum properties of the system.
  arXiv  Detail & Related papers  (2020-06-20T10:07:01Z)

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.