Fixed-kinetic Neural Hamiltonian Flows for enhanced interpretability and reduced complexity

• URL: http://arxiv.org/abs/2302.01955v1
• Date: Fri, 3 Feb 2023 19:05:57 GMT
• Title: Fixed-kinetic Neural Hamiltonian Flows for enhanced interpretability and reduced complexity
• Authors: Vincent Souveton, Arnaud Guillin, Jens Jasche, Guilhem Lavaux, Manon Michel
• Abstract summary: We introduce a fixed kinetic energy version of the Neural Hamiltonian Flows (NHF) model. Inspired by physics, our approach improves interpretability and requires less parameters than previously proposed architectures. We also adapt NHF to the context of Bayesian inference and illustrate our method on sampling the posterior distribution of two cosmological parameters.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Normalizing Flows (NF) are Generative models which are particularly robust and allow for exact sampling of the learned distribution. They however require the design of an invertible mapping, whose Jacobian determinant has to be computable. Recently introduced, Neural Hamiltonian Flows (NHF) are based on Hamiltonian dynamics-based Flows, which are continuous, volume-preserving and invertible and thus make for natural candidates for robust NF architectures. In particular, their similarity to classical Mechanics could lead to easier interpretability of the learned mapping. However, despite being Physics-inspired architectures, the originally introduced NHF architecture still poses a challenge to interpretability. For this reason, in this work, we introduce a fixed kinetic energy version of the NHF model. Inspired by physics, our approach improves interpretability and requires less parameters than previously proposed architectures. We then study the robustness of the NHF architectures to the choice of hyperparameters. We analyze the impact of the number of leapfrog steps, the integration time and the number of neurons per hidden layer, as well as the choice of prior distribution, on sampling a multimodal 2D mixture. The NHF architecture is robust to these choices, especially the fixed-kinetic energy model. Finally, we adapt NHF to the context of Bayesian inference and illustrate our method on sampling the posterior distribution of two cosmological parameters knowing type Ia supernovae observations.

Related papers

• HFNO: an interpretable data-driven decomposition strategy for turbulent flows [0.0]
  We present a novel FNO-based architecture tailored for reduced-order modeling of turbulent fluid flows.<n>The proposed architecture processes wavenumber bins in parallel, enabling approximation of dispersion relations and non-linear interactions.<n>We evaluate the proposed model on a series of increasingly complex dynamical systems.
  arXiv  Detail & Related papers  (2025-11-03T12:57:19Z)
• Curly Flow Matching for Learning Non-gradient Field Dynamics [49.480209466896035]
  We introduce Curly Flow Matching (Curly-FM), a novel approach to learning non-gradient field dynamics.<n>Curly-FM is capable of learning non-gradient field dynamics by designing and solving a Schr"odinger bridge problem.<n>Curly-FM can learn trajectories that better match both the reference process and population marginals.
  arXiv  Detail & Related papers  (2025-10-30T16:11:39Z)
• Floating-Body Hydrodynamic Neural Networks [8.501171043928354]
  We propose a physics-structured framework that predicts interpretable parameters such as directional added masses, drag coefficients, and a streamfunction-based flow, and couples them with analytic equations of motion.<n>Compared with Hamiltonian and Lagrangian neural networks, FHNN more effectively handles dissipative dynamics while preserving interpretability, which bridges the gap between black-box learning and transparent system identification.
  arXiv  Detail & Related papers  (2025-09-17T07:51:35Z)
• Langevin Flows for Modeling Neural Latent Dynamics [81.81271685018284]
  We introduce LangevinFlow, a sequential Variational Auto-Encoder where the time evolution of latent variables is governed by the underdamped Langevin equation.<n>Our approach incorporates physical priors -- such as inertia, damping, a learned potential function, and forces -- to represent both autonomous and non-autonomous processes in neural systems.<n>Our method outperforms state-of-the-art baselines on synthetic neural populations generated by a Lorenz attractor.
  arXiv  Detail & Related papers  (2025-07-15T17:57:48Z)
• High-order Equivariant Flow Matching for Density Functional Theory Hamiltonian Prediction [14.957565545353942]
  deep learning methods are gaining attention as a way to bypass this step by directly predicting the Hamiltonian.<n>We propose QHFlow, a high-order equivariant flow matching framework that generates Hamiltonian matrices conditioned on molecular geometry.<n>Flow matching models continuous-time trajectories between simple priors and complex targets, learning the structured distributions over Hamiltonians instead of direct regression.
  arXiv  Detail & Related papers  (2025-05-24T18:23:28Z)
• KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches [43.872190335490515]
  This paper introduces KITINet, a novel architecture that reinterprets feature propagation through the lens of non-equilibrium particle dynamics.<n>At its core, we propose a residual module that models update as the evolution of a particle system.<n>This formulation mimics particle collisions and energy exchange, enabling adaptive feature refinement via physics-informed interactions.
  arXiv  Detail & Related papers  (2025-05-23T13:58:29Z)
• Symplectic Neural Flows for Modeling and Discovery [9.786274281068815]
  SympFlow is a time-dependent symplectic neural network designed using parameterized Hamiltonian flow maps. It allows for backward error analysis and ensures the preservation of the symplectic structure. We demonstrate the effectiveness of SympFlow on diverse problems, including chaotic and dissipative systems.
  arXiv  Detail & Related papers  (2024-12-21T22:02:00Z)
• Latent Space Energy-based Neural ODEs [73.01344439786524]
  This paper introduces a novel family of deep dynamical models designed to represent continuous-time sequence data. We train the model using maximum likelihood estimation with Markov chain Monte Carlo. Experiments on oscillating systems, videos and real-world state sequences (MuJoCo) illustrate that ODEs with the learnable energy-based prior outperform existing counterparts.
  arXiv  Detail & Related papers  (2024-09-05T18:14:22Z)
• Fourier Neural Operators for Learning Dynamics in Quantum Spin Systems [77.88054335119074]
  We use FNOs to model the evolution of random quantum spin systems. We apply FNOs to a compact set of Hamiltonian observables instead of the entire $2n$ quantum wavefunction.
  arXiv  Detail & Related papers  (2024-09-05T07:18:09Z)
• Deep Neural Networks as Variational Solutions for Correlated Open Quantum Systems [0.0]
  We show that parametrizing the density matrix directly with more powerful models can yield better variational ansatz functions. We present results for the dissipative one-dimensional transverse-field Ising model and a two-dimensional dissipative Heisenberg model.
  arXiv  Detail & Related papers  (2024-01-25T13:41:34Z)
• Applications of Machine Learning to Modelling and Analysing Dynamical Systems [0.0]
  We propose an architecture which combines existing Hamiltonian Neural Network structures into Adaptable Symplectic Recurrent Neural Networks. This architecture is found to significantly outperform previously proposed neural networks when predicting Hamiltonian dynamics. We show that this method works efficiently for single parameter potentials and provides accurate predictions even over long periods of time.
  arXiv  Detail & Related papers  (2023-07-22T19:04:17Z)
• 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)
• Capturing dynamical correlations using implicit neural representations [85.66456606776552]
  We develop an artificial intelligence framework which combines a neural network trained to mimic simulated data from a model Hamiltonian with automatic differentiation to recover unknown parameters from experimental data. In doing so, we illustrate the ability to build and train a differentiable model only once, which then can be applied in real-time to multi-dimensional scattering data.
  arXiv  Detail & Related papers  (2023-04-08T07:55:36Z)
• A predictive physics-aware hybrid reduced order model for reacting flows [65.73506571113623]
  A new hybrid predictive Reduced Order Model (ROM) is proposed to solve reacting flow problems. The number of degrees of freedom is reduced from thousands of temporal points to a few POD modes with their corresponding temporal coefficients. Two different deep learning architectures have been tested to predict the temporal coefficients.
  arXiv  Detail & Related papers  (2023-01-24T08:39:20Z)
• Positive-definite parametrization of mixed quantum states with deep neural networks [0.0]
  We show how to embed an autoregressive structure in the GHDO to allow direct sampling of the probability distribution. We benchmark this architecture by the steady state of the dissipative transverse-field Ising model.
  arXiv  Detail & Related papers  (2022-06-27T17:51:38Z)
• GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation [102.85440102147267]
  We propose a novel generative model named GeoDiff for molecular conformation prediction. We show that GeoDiff is superior or comparable to existing state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-03-06T09:47:01Z)
• Moser Flow: Divergence-based Generative Modeling on Manifolds [49.04974733536027]
  Moser Flow (MF) is a new class of generative models within the family of continuous normalizing flows (CNF) MF does not require invoking or backpropagating through an ODE solver during training. We demonstrate for the first time the use of flow models for sampling from general curved surfaces.
  arXiv  Detail & Related papers  (2021-08-18T09:00:24Z)
• Discrete Denoising Flows [87.44537620217673]
  We introduce a new discrete flow-based model for categorical random variables: Discrete Denoising Flows (DDFs) In contrast with other discrete flow-based models, our model can be locally trained without introducing gradient bias. We show that DDFs outperform Discrete Flows on modeling a toy example, binary MNIST and Cityscapes segmentation maps, measured in log-likelihood.
  arXiv  Detail & Related papers  (2021-07-24T14:47:22Z)
• E(n) Equivariant Normalizing Flows for Molecule Generation in 3D [87.12477361140716]
  This paper introduces a generative model equivariant to Euclidean symmetries: E(n) Equivariant Normalizing Flows (E-NFs) To the best of our knowledge, this is the first likelihood-based deep generative model that generates molecules in 3D.
  arXiv  Detail & Related papers  (2021-05-19T09:28:54Z)
• A unified framework for Hamiltonian deep neural networks [3.0934684265555052]
  Training deep neural networks (DNNs) can be difficult due to vanishing/exploding gradients during weight optimization. We propose a class of DNNs stemming from the time discretization of Hamiltonian systems. The proposed Hamiltonian framework, besides encompassing existing networks inspired by marginally stable ODEs, allows one to derive new and more expressive architectures.
  arXiv  Detail & Related papers  (2021-04-27T13:20:24Z)
• Graphical Normalizing Flows [11.23030807455021]
  Normalizing flows model complex probability distributions by combining a base distribution with a series of neural networks. State-of-the-art architectures rely on coupling and autoregressive transformations to lift up invertible functions from scalars to vectors. We propose the graphical normalizing flow, a new invertible transformation with either a prescribed or a learnable graphical structure.
  arXiv  Detail & Related papers  (2020-06-03T21:50:29Z)
• Machine learning based non-Newtonian fluid model with molecular fidelity [17.93540781757586]
  We introduce a machine-learning-based framework for constructing continuum non-Newtonian fluid dynamics model. Dumbbell polymer solutions are used as examples to demonstrate the essential ideas.
  arXiv  Detail & Related papers  (2020-03-07T22:24:34Z)

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.