Numerically Solving Parametric Families of High-Dimensional Kolmogorov Partial Differential Equations via Deep Learning

被引:0
作者
Berner, Julius [1 ]
Dablander, Markus [2 ]
Grohs, Philipp [1 ,3 ,4 ]
机构
[1] Univ Vienna, Fac Math, Oskar Morgenstern Pl 1, A-1090 Vienna, Austria
[2] Univ, Math Inst, Andrew Wiles Bldg, Oxford OX2 6GG, England
[3] Univ Vienna, Res Platform DataSci UniVienna, Oskar Morgenstern Pl 1, A-1090 Vienna, Austria
[4] Austrian Acad Sci, RICAM, Altenberger Str 69, A-4040 Linz, Austria
来源
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020 | 2020年 / 33卷
基金
奥地利科学基金会; 英国工程与自然科学研究理事会;
关键词
APPROXIMATION; ALGORITHM; MODELS;
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
We present a deep learning algorithm for the numerical solution of parametric families of high-dimensional linear Kolmogorov partial differential equations (PDEs). Our method is based on reformulating the numerical approximation of a whole family of Kolmogorov PDEs as a single statistical learning problem using the Feynman-Kac formula. Successful numerical experiments are presented, which empirically confirm the functionality and efficiency of our proposed algorithm in the case of heat equations and Black-Scholes option pricing models parametrized by affine-linear coefficient functions. We show that a single deep neural network trained on simulated data is capable of learning the solution functions of an entire family of PDEs on a full space-time region. Most notably, our numerical observations and theoretical results also demonstrate that the proposed method does not suffer from the curse of dimensionality, distinguishing it from almost all standard numerical methods for PDEs.
引用
收藏
页数:13
相关论文
共 62 条
[1]  
Aliprantis C.D., 2006, Infinite Dimensional Analysis: A Hitchhiker's Guide
[2]  
Ames W.F, 2014, Numerical methods for partial differential equations
[3]  
[Anonymous], 2019, IEEE Trans. Inform. Theory
[4]  
[Anonymous], 2017, ARXIV170703351
[5]  
[Anonymous], 2019, 2019 13 INT C SAMPL
[6]  
[Anonymous], 1992, Bulletin of the American mathematical society
[7]  
[Anonymous], J NONLINEAR SCI
[8]  
BALDI P., 2017, Stochastic calculus. Universitext
[9]  
Beck C., 2018, ARXIV180600421
[10]   Machine Learning Approximation Algorithms for High-Dimensional Fully Nonlinear Partial Differential Equations and Second-order Backward Stochastic Differential Equations [J].
Beck, Christian ;
Weinan, E. ;
Jentzen, Arnulf .
JOURNAL OF NONLINEAR SCIENCE, 2019, 29 (04) :1563-1619