PINF: Continuous Normalizing Flows for Physics-Constrained Deep Learning

• URL: http://arxiv.org/abs/2309.15139v1
• Date: Tue, 26 Sep 2023 15:38:57 GMT
• Title: PINF: Continuous Normalizing Flows for Physics-Constrained Deep Learning
• Abstract summary: In this paper, we introduce Physics-Informed Normalizing Flows (PINF), a novel extension of continuous normalizing flows. Our method, which is mesh-free and causality-free, can efficiently solve high dimensional time-dependent and steady-state Fokker-Planck equations.
• Score: 8.000355537589224
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The normalization constraint on probability density poses a significant challenge for solving the Fokker-Planck equation. Normalizing Flow, an invertible generative model leverages the change of variables formula to ensure probability density conservation and enable the learning of complex data distributions. In this paper, we introduce Physics-Informed Normalizing Flows (PINF), a novel extension of continuous normalizing flows, incorporating diffusion through the method of characteristics. Our method, which is mesh-free and causality-free, can efficiently solve high dimensional time-dependent and steady-state Fokker-Planck equations.

Related papers

• QH-GEM: Quantum-Hydrodynamic Generative Modeling [0.0]
  We develop a deterministic, physically constrained generative framework based on the Madelung formulation of the free-particle Schrdinger equation.<n>A reference Born probability density and a controllable initial phase function serve as initial data for the free Madelung system.<n>For isotropic Gaussian wave packets, we obtain explicit dynamics and a necessary and sufficient condition for exact reachability of isotropic targets.
  arXiv  Detail & Related papers  (2026-08-27T14:57:08Z)
• Simplifying Flow Matching Transformations with Low-Rank Mixture Models [58.797704398690165]
  We propose using mixtures of probabilistic principal component analyzers (MPPCA) as the latent density for normalizing flows.<n>We simplify the learned flow transformation by learning a latent distribution that more closely aligns with the data distribution in terms of KL divergence.<n>MPPCA models can be fit quickly and cheaply using the expectation-maximization algorithm, making them a practical choice for initializing latent distributions even in high-dimensional generative tasks.
  arXiv  Detail & Related papers  (2026-06-29T03:03:06Z)
• Operator learning for solving Fokker-Planck equations with various initial conditions [9.218744685480125]
  The Fokker-Planck equation (FPE) plays a pivotal role in describing the time evolution of density functions (PDFs)<n>We propose a conditional normalizing flow-based physics-informed neural network (PINN) framework for efficiently approximating the solution operator of the FPE.<n>A variety of numerical experiments are presented to illustrate the effectiveness and robustness of the proposed method.
  arXiv  Detail & Related papers  (2026-06-08T12:44:13Z)
• Neural Galerkin Normalizing Flow for Transition Probability Density Functions of Diffusion Models [0.0]
  We propose a new framework to approximate the transition probability density function of a diffusion process.<n>We look for the solution as a transformation of the transition probability density function of a reference process.<n>We derive a system of ODEs for the time evolution of the Normalizing Flow's parameters.
  arXiv  Detail & Related papers  (2026-03-19T13:43:18Z)
• EFF-Grasp: Energy-Field Flow Matching for Physics-Aware Dexterous Grasp Generation [54.09734511705173]
  EFF-Grasp is a Flow-Matching synthesis-based framework for physics-aware dexterous grasp generation.<n>We reformulate grasp as a deterministic ordinary differential equation (ODE) process, which enables efficient and stable generation through smooth probability flows.<n> EFF-Grasp achieves superior performance in grasp quality and physical feasibility, while requiring substantially fewer sampling steps than diffusion-based baselines.
  arXiv  Detail & Related papers  (2026-03-17T06:11:56Z)
• Simulation-Free Differential Dynamics through Neural Conservation Laws [22.4113724471297]
  We present a novel simulation-free framework for training continuous-time diffusion processes over very general objective functions.<n>We propose a coupled parameterization which jointly models a time-dependent density function, or probability path, and the dynamics of a diffusion process that generates this probability path.
  arXiv  Detail & Related papers  (2025-06-23T13:04:23Z)
• FlowKac: An Efficient Neural Fokker-Planck solver using Temporal Normalizing flows and the Feynman Kac-Formula [4.806505912512236]
  FlowKac is a novel approach that reformulates the Fokker-Planck equation using the Feynman-Kac formula. A key innovation of FlowKac lies in its adaptive sampling scheme which significantly reduces the computational complexity.
  arXiv  Detail & Related papers  (2025-03-14T14:14:20Z)
• Lagrangian Flow Networks for Conservation Laws [1.3385962626827215]
  We introduce Lagrangian Flow Networks (LFlows) for modeling fluid densities and velocities continuously in space and time. LFlows show higher predictive accuracy in density modeling tasks compared to competing models in 2D and 3D. As a real-world application, we model bird migration based on sparse weather radar measurements.
  arXiv  Detail & Related papers  (2023-05-26T11:58:27Z)
• ManiFlow: Implicitly Representing Manifolds with Normalizing Flows [145.9820993054072]
  Normalizing Flows (NFs) are flexible explicit generative models that have been shown to accurately model complex real-world data distributions. We propose an optimization objective that recovers the most likely point on the manifold given a sample from the perturbed distribution. Finally, we focus on 3D point clouds for which we utilize the explicit nature of NFs, i.e. surface normals extracted from the gradient of the log-likelihood and the log-likelihood itself.
  arXiv  Detail & Related papers  (2022-08-18T16:07:59Z)
• Self-Consistency of the Fokker-Planck Equation [117.17004717792344]
  The Fokker-Planck equation governs the density evolution of the Ito process. Ground-truth velocity field can be shown to be the solution of a fixed-point equation. In this paper, we exploit this concept to design a potential function of the hypothesis velocity fields.
  arXiv  Detail & Related papers  (2022-06-02T03:44:23Z)
• Discretely Indexed Flows [1.0079626733116611]
  We propose Discretely Indexed flows (DIF) as a new tool for solving variational estimation problems. DIF are built as an extension of Normalizing Flows (NF), in which the deterministic transport becomes discretely indexed. They benefit from both a tractable density as well as a straightforward sampling scheme, and can thus be used for the dual problems of Variational Inference (VI) and of Variational density estimation (VDE)
  arXiv  Detail & Related papers  (2022-04-04T10:13:43Z)
• Solving time dependent Fokker-Planck equations via temporal normalizing flow [7.3990175502763185]
  We propose an adaptive learning approach based on temporal normalizing flows for solving time-dependent Fokker-Planck equations. Being a machine learning scheme, the proposed approach is mesh-free and can be easily applied to high dimensional problems.
  arXiv  Detail & Related papers  (2021-12-28T06:39:14Z)
• Normalizing Field Flows: Solving forward and inverse stochastic differential equations using Physics-Informed flow model [8.455584500599807]
  We introduce in this work the normalizing field flows (NFF) for learning random fields from scattered measurements. We demonstrate the capability of the proposed NFF model for learning Non Gaussian processes, mixed Gaussian processes, and forward & inverse partial differential equations.
  arXiv  Detail & Related papers  (2021-08-30T01:58:01Z)
• 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)
• Large-Scale Wasserstein Gradient Flows [84.73670288608025]
  We introduce a scalable scheme to approximate Wasserstein gradient flows. Our approach relies on input neural networks (ICNNs) to discretize the JKO steps. As a result, we can sample from the measure at each step of the gradient diffusion and compute its density.
  arXiv  Detail & Related papers  (2021-06-01T19:21:48Z)
• Integrable Nonparametric Flows [5.9774834479750805]
  We introduce a method for reconstructing an infinitesimal normalizing flow given only an infinitesimal change to a probability distribution. This reverses the conventional task of normalizing flows. We discuss potential applications to problems in quantum Monte Carlo and machine learning.
  arXiv  Detail & Related papers  (2020-12-03T16:19:52Z)
• Learning Likelihoods with Conditional Normalizing Flows [54.60456010771409]
  Conditional normalizing flows (CNFs) are efficient in sampling and inference. We present a study of CNFs where the base density to output space mapping is conditioned on an input x, to model conditional densities p(y|x)
  arXiv  Detail & Related papers  (2019-11-29T19:17:58Z)
• A Near-Optimal Gradient Flow for Learning Neural Energy-Based Models [93.24030378630175]
  We propose a novel numerical scheme to optimize the gradient flows for learning energy-based models (EBMs) We derive a second-order Wasserstein gradient flow of the global relative entropy from Fokker-Planck equation. Compared with existing schemes, Wasserstein gradient flow is a smoother and near-optimal numerical scheme to approximate real data densities.
  arXiv  Detail & Related papers  (2019-10-31T02:26:20Z)

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.