A deep learning method for solving Fokker-Planck equations

被引:0
|
作者
Zhai, Jiayu [1 ]
Dobson, Matthew [1 ]
Li, Yao [1 ]
机构
[1] Univ Massachusetts, Dept Math & Stat, Amherst, MA 01002 USA
来源
MATHEMATICAL AND SCIENTIFIC MACHINE LEARNING, VOL 145 | 2021年 / 145卷
关键词
Stochastic differential equation; Monte Carlo simulation; invariant measure; coupling method; data-driven and machine learning methods; APPROXIMATION; ALGORITHMS;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The time evolution of the probability distribution of a stochastic differential equation follows the Fokker-Planck equation, which usually has an unbounded, high-dimensional domain. Inspired by Li (2019), we propose a mesh-free Fokker-Planck solver, in which the solution to the Fokker-Planck equation is now represented by a neural network. The presence of the differential operator in the loss function improves the accuracy of the neural network representation and reduces the demand of data in the training process. Several high dimensional numerical examples are demonstrated.
引用
收藏
页码:568 / 597
页数:30
相关论文
共 50 条
  • [41] Thermodynamics and fractional Fokker-Planck equations
    Sokolov, IM
    PHYSICAL REVIEW E, 2001, 63 (05):
  • [42] Generalized Stochastic Fokker-Planck Equations
    Chavanis, Pierre-Henri
    ENTROPY, 2015, 17 (05) : 3205 - 3252
  • [43] Solution of nonlinear Fokker-Planck equations
    Drozdov, AN
    Morillo, M
    PHYSICAL REVIEW E, 1996, 54 (01): : 931 - 937
  • [44] Deformed multivariable fokker-planck equations
    Ho, Choon-Lin
    Sasaki, Ryu
    JOURNAL OF MATHEMATICAL PHYSICS, 2007, 48 (07)
  • [45] Periodic solutions of Fokker-Planck equations
    Chen, Feng
    Han, Yuecai
    Li, Yong
    Yang, Xue
    JOURNAL OF DIFFERENTIAL EQUATIONS, 2017, 263 (01) : 285 - 298
  • [46] Convergence to Equilibrium in Fokker-Planck Equations
    Ji, Min
    Shen, Zhongwei
    Yi, Yingfei
    JOURNAL OF DYNAMICS AND DIFFERENTIAL EQUATIONS, 2019, 31 (03) : 1591 - 1615
  • [47] DIFFERENTIAL EQUATIONS OF FOKKER-PLANCK TYPE
    KRATZEL, E
    MATHEMATISCHE NACHRICHTEN, 1967, 35 (3-4) : 137 - &
  • [48] A quadrature based method of moments for nonlinear Fokker-Planck equations
    Otten, Dustin L.
    Vedula, Prakash
    JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT, 2011,
  • [49] Fokker-Planck equations method in theory of multilevel atoms relaxation
    Gorokhov, AV
    Mikhailov, VA
    PHOTON ECHO AND COHERENT SPECTROSCOPY '97, 1997, 3239 : 256 - 260
  • [50] SOLVING DIFFERENTIAL-EQUATIONS BY A MAXIMUM-ENTROPY MINIMUM NORM METHOD WITH APPLICATIONS TO FOKKER-PLANCK EQUATIONS
    BAKERJARVIS, J
    RACINE, M
    ALAMEDDINE, J
    JOURNAL OF MATHEMATICAL PHYSICS, 1989, 30 (07) : 1459 - 1463