paper-with-me

Papers

Transport based particle methods for the Fokker-Planck-Landau equation

2024-05-16 · Vasily Ilin, Jingwei Hu, Zhenfu Wang

We propose a particle method for numerically solving the Landau equation, inspired by the score-based transport modeling (SBTM) method for the Fokker-Planck equation. This method can preserve some important physical properties of the Landau equation, such as the conservation of mass, momentum, and energy, and decay of estimated entropy. We prove that matching the gradient of the logarithm of the approximate solution is enough to recover the true solution to the Landau equation with Maxwellian molecules. Several numerical experiments in low and moderately high dimensions are performed, with particular emphasis on comparing the proposed method with the traditional particle or blob method.

📄 PDF Abstract BibTeX arXiv:2405.10392

Code (1)

vilin97/gradientflows.jl 공식 구현

Similar Papers 제목 키워드 기반

Score-based Transport Modeling for Mean-Field Fokker-Planck Equations

2023-04-21 · Jianfeng Lu, Yue Wu, Yang Xiang

We use the score-based transport modeling method to solve the mean-field Fokker-Planck equations, which we call MSBTM. We establish an upper bound on the time derivative of the Kullback-Leibler (KL) divergence to MSBTM n…

Encoder-decoder neural network for solving the nonlinear Fokker-Planck-Landau collision operator in XGC

2020-02-26 · ICLR Workshop DeepDiffEq 2019 12 · Marco Andres Miller, Randy Michael Churchill, Choong-Seock Chang, Robert Hager

An encoder-decoder neural network has been used to accelerate the numerical solving of a partial integro-differential equation, the Fokker-Planck-Landau collision operator. This is part of the governing equation in the m…

Decoder

Deterministic Fokker-Planck Transport -- With Applications to Sampling, Variational Inference, Kernel Mean Embeddings & Sequential Monte Carlo

2024-10-11 · Ilja Klebanov

The Fokker-Planck equation can be reformulated as a continuity equation, which naturally suggests using the associated velocity field in particle flow methods. While the resulting probability flow ODE offers appealing pr…

Density EstimationVariational Inference

opPINN: Physics-Informed Neural Network with operator learning to approximate solutions to the Fokker-Planck-Landau equation

2022-07-05 · Jae Yong Lee, Juhi Jang, Hyung Ju Hwang

We propose a hybrid framework opPINN: physics-informed neural network (PINN) with operator learning for approximating the solution to the Fokker-Planck-Landau (FPL) equation. The opPINN framework is divided into two step…

Operator learning

Closing the ODE-SDE gap in score-based diffusion models through the Fokker-Planck equation

2023-11-27 · Teo Deveney, Jan Stanczuk, Lisa Maria Kreusser, Chris Budd 외

Score-based diffusion models have emerged as one of the most promising frameworks for deep generative modelling, due to their state-of-the art performance in many generation tasks while relying on mathematical foundation…