Machine Learning for Semi Linear PDEs

被引：66
作者：
Chan-Wai-Nam, Quentin [1 ]
Mikael, Joseph [1 ]
Warin, Xavier [1 ,2 ]
机构：
[1] EDF Lab Paris Saclay, Palaiseau, France
[2] FiME, Lab Finance Marches Energie, Chatou, France
来源：
JOURNAL OF SCIENTIFIC COMPUTING | 2019年 / 79卷 / 03期
关键词：
Semilinear PDEs; Monte-Carlo methods; Machine learning; Deep learning;
D O I：
10.1007/s10915-019-00908-3
中图分类号：
O29 [应用数学];
学科分类号：
070104 ;
摘要：
Recent machine learning algorithms dedicated to solving semi-linear PDEs are improved by using different neural network architectures and different parameterizations. These algorithms are compared to a new one that solves a fixed point problem by using deep learning techniques. This new algorithm appears to be competitive in terms of accuracy with the best existing algorithms.
引用
收藏
页码：1667 / 1712
页数：46
相关论文
共 43 条
  • [1] [Anonymous], 2017, ARXIV170107660
  • [2] [Anonymous], 2017, ARXIV170702568
  • [3] [Anonymous], ARXIV160301727
  • [4] [Anonymous], 2017, ARXIV170905963
  • [5] Bengio Yoshua, 2012, Neural Networks: Tricks of the Trade. Second Edition: LNCS 7700, P437, DOI 10.1007/978-3-642-35289-8_26
  • [6] Discrete-time approximation and Monte-Carlo simulation of backward stochastic differential equations
    Bouchard, B
    Touzi, N
    [J]. STOCHASTIC PROCESSES AND THEIR APPLICATIONS, 2004, 111 (02) : 175 - 206
  • [7] Bouchard B., 2012, Numerical Methods in Finance, P215
  • [8] Bouchard B., 2017, ESAIM P SURVEYS
  • [9] Bouchard B, 2017, MONTE CARLO METHODS, V23, P241, DOI 10.1515/mcma-2017-0116
  • [10] Braun S., 2018, ARXIV180601818
12345