paper-with-me

홈 › Papers

Neural network representation of the probability density function of diffusion processes

2020-01-15 · Wayne Isaac Tan Uy, Mircea Grigoriu

Physics-informed neural networks are developed to characterize the state of dynamical systems in a random environment. The neural network approximates the probability density function (pdf) or the characteristic function (chf) of the state of these systems which satisfy the Fokker-Planck equation or an integro-differential equation under Gaussian and/or Poisson white noises. We examine analytically and numerically the advantages and disadvantages of solving each type of differential equation to characterize the state. It is also demonstrated how prior information of the dynamical system can be exploited to design and simplify the neural network architecture. Numerical examples show that: 1) the neural network solution can approximate the target solution even for partial integro-differential equations and system of PDEs describing the time evolution of the pdf/chf, 2) solving either the Fokker-Planck equation or the chf differential equation using neural networks yields similar pdfs of the state, and 3) the solution to these differential equations can be used to study the behavior of the state for different types of random forcings.

📄 PDF Abstract BibTeX arXiv:2001.05437

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Stochastic Interpolants: A Unifying Framework for Flows and Diffusions

2023-03-15 · Michael S. Albergo, Nicholas M. Boffi, Eric Vanden-Eijnden

A class of generative models that unifies flow-based and diffusion-based methods is introduced. These models extend the framework proposed in Albergo & Vanden-Eijnden (2023), enabling the use of a broad class of continuo…

Denoising

Riemannian Gaussian distributions, random matrix ensembles and diffusion kernels

2020-11-27 · Leonardo Santilli, Miguel Tierz

We show that the Riemannian Gaussian distributions on symmetric spaces, introduced in recent years, are of standard random matrix type. We exploit this to compute analytically marginals of the probability density functio…

Closed-form conditional diffusion models for data assimilation

2026-03-22 · Brianna Binder, Agnimitra Dasgupta, Assad Oberai arxiv

We propose closed-form conditional diffusion models for data assimilation. Diffusion models use data to learn the score function (defined as the gradient of the log-probability density of a data distribution), allowing t…

Density Estimation

Density Stabilization Strategies for Nonholonomic Agents on Compact Manifolds

2023-08-30 · Karthik Elamvazhuthi, Spring Berman

In this article, we consider the problem of stabilizing stochastic processes, which are constrained to a bounded Euclidean domain or a compact smooth manifold, to a given target probability density. Most existing works o…

Large-Scale Wasserstein Gradient Flows

2021-06-01 · NeurIPS 2021 12 · Petr Mokrov, Alexander Korotin, Lingxiao Li, Aude Genevay 외

Wasserstein gradient flows provide a powerful means of understanding and solving many diffusion equations. Specifically, Fokker-Planck equations, which model the diffusion of probability measures, can be understood as gr…