Solution of FPK Equation for Stochastic Dynamics Subjected to Additive Gaussian Noise via Deep Learning Approach

• URL: http://arxiv.org/abs/2311.04511v1
• Date: Wed, 8 Nov 2023 07:57:21 GMT
• Title: Solution of FPK Equation for Stochastic Dynamics Subjected to Additive Gaussian Noise via Deep Learning Approach
• Authors: Amir H. Khodabakhsh, Seid H. Pourtakdoust
• Abstract summary: The Fokker-Plank-Kolmogorov (FPK) equation is an idealized model representing many systems commonly encountered in the analysis of structures as well as many other applications. Despite its great importance, the solution of the FPK equation is still extremely challenging. The present work introduces the FPK-DP Net as a physics-informed network that encodes the physical insights.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The Fokker-Plank-Kolmogorov (FPK) equation is an idealized model representing many stochastic systems commonly encountered in the analysis of stochastic structures as well as many other applications. Its solution thus provides an invaluable insight into the performance of many engineering systems. Despite its great importance, the solution of the FPK equation is still extremely challenging. For systems of practical significance, the FPK equation is usually high dimensional, rendering most of the numerical methods ineffective. In this respect, the present work introduces the FPK-DP Net as a physics-informed network that encodes the physical insights, i.e. the governing constrained differential equations emanated out of physical laws, into a deep neural network. FPK-DP Net is a mesh-free learning method that can solve the density evolution of stochastic dynamics subjected to additive white Gaussian noise without any prior simulation data and can be used as an efficient surrogate model afterward. FPK-DP Net uses the dimension-reduced FPK equation. Therefore, it can be used to address high-dimensional practical problems as well. To demonstrate the potential applicability of the proposed framework, and to study its accuracy and efficacy, numerical implementations on five different benchmark problems are investigated.

Related papers

• Learning Controlled Stochastic Differential Equations [61.82896036131116]
  This work proposes a novel method for estimating both drift and diffusion coefficients of continuous, multidimensional, nonlinear controlled differential equations with non-uniform diffusion. We provide strong theoretical guarantees, including finite-sample bounds for (L2), (Linfty), and risk metrics, with learning rates adaptive to coefficients' regularity. Our method is available as an open-source Python library.
  arXiv  Detail & Related papers  (2024-11-04T11:09:58Z)
• DimOL: Dimensional Awareness as A New 'Dimension' in Operator Learning [63.5925701087252]
  We introduce DimOL (Dimension-aware Operator Learning), drawing insights from dimensional analysis. To implement DimOL, we propose the ProdLayer, which can be seamlessly integrated into FNO-based and Transformer-based PDE solvers. Empirically, DimOL models achieve up to 48% performance gain within the PDE datasets.
  arXiv  Detail & Related papers  (2024-10-08T10:48:50Z)
• Solving Poisson Equations using Neural Walk-on-Spheres [80.1675792181381]
  We propose Neural Walk-on-Spheres (NWoS), a novel neural PDE solver for the efficient solution of high-dimensional Poisson equations. We demonstrate the superiority of NWoS in accuracy, speed, and computational costs.
  arXiv  Detail & Related papers  (2024-06-05T17:59:22Z)
• HyperSINDy: Deep Generative Modeling of Nonlinear Stochastic Governing Equations [5.279268784803583]
  We introduce HyperSINDy, a framework for modeling dynamics via a deep generative model of sparse governing equations from data. Once trained, HyperSINDy generates dynamics via a differential equation whose coefficients are driven by a white noise. In experiments, HyperSINDy recovers ground truth governing equations, with learnedity scaling to match that of the data.
  arXiv  Detail & Related papers  (2023-10-07T14:41:59Z)
• Physics-Informed Solution of The Stationary Fokker-Plank Equation for a Class of Nonlinear Dynamical Systems: An Evaluation Study [0.0]
  An exact analytical solution of the Fokker-Planck (FP) equation is only available for a limited subset of dynamical systems. To evaluate its potential, we present a data-free, physics-informed neural network (PINN) framework to solve the FP equation.
  arXiv  Detail & Related papers  (2023-09-25T13:17:34Z)
• Implicit Stochastic Gradient Descent for Training Physics-informed Neural Networks [51.92362217307946]
  Physics-informed neural networks (PINNs) have effectively been demonstrated in solving forward and inverse differential equation problems. PINNs are trapped in training failures when the target functions to be approximated exhibit high-frequency or multi-scale features. In this paper, we propose to employ implicit gradient descent (ISGD) method to train PINNs for improving the stability of training process.
  arXiv  Detail & Related papers  (2023-03-03T08:17:47Z)
• D4FT: A Deep Learning Approach to Kohn-Sham Density Functional Theory [79.50644650795012]
  We propose a deep learning approach to solve Kohn-Sham Density Functional Theory (KS-DFT) We prove that such an approach has the same expressivity as the SCF method, yet reduces the computational complexity. In addition, we show that our approach enables us to explore more complex neural-based wave functions.
  arXiv  Detail & Related papers  (2023-03-01T10:38:10Z)
• A Deep Learning Approach for the solution of Probability Density Evolution of Stochastic Systems [0.0]
  DeepPDEM utilizes the concept of physics-informed networks to solve the evolution of the probability density. DeepPDEM learns the General Density Evolution Equation (GDEE) of structures. It can also serve as an efficient surrogate for the solution at any points within optimization schemes or real-time applica-tions.
  arXiv  Detail & Related papers  (2022-07-05T09:37:48Z)
• Deep Graphic FBSDEs for Opinion Dynamics Stochastic Control [27.38625075499457]
  We present a scalable deep learning approach to solve opinion dynamics optimal control problems with mean field term coupling in the dynamics and cost function. The proposed framework opens up the possibility for future applications on extremely large-scale problems.
  arXiv  Detail & Related papers  (2022-04-05T22:07:32Z)
• Physics-constrained Unsupervised Learning of Partial Differential Equations using Meshes [1.066048003460524]
  Graph neural networks show promise in accurately representing irregularly meshed objects and learning their dynamics. In this work, we represent meshes naturally as graphs, process these using Graph Networks, and formulate our physics-based loss to provide an unsupervised learning framework for partial differential equations (PDE) Our framework will enable the application of PDE solvers in interactive settings, such as model-based control of soft-body deformations.
  arXiv  Detail & Related papers  (2022-03-30T19:22:56Z)
• Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid Flow Prediction [79.81193813215872]
  We develop a hybrid (graph) neural network that combines a traditional graph convolutional network with an embedded differentiable fluid dynamics simulator inside the network itself. We show that we can both generalize well to new situations and benefit from the substantial speedup of neural network CFD predictions.
  arXiv  Detail & Related papers  (2020-07-08T21:23:19Z)

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.