Variational Monte Carlo-bridging concepts of machine learning and high-dimensional partial differential equations

被引：19

作者：

Eigel, Martin ^{[1
]}

Schneider, Reinhold ^{[2
]}

Trunschke, Philipp ^{[2
]}

Wolf, Sebastian ^{[1
,2
]}

机构：

[1] Weierstrass Inst, Mohrenstr 39, D-10117 Berlin, Germany

[2] TU Berlin, Str 17 Juni 136, D-10623 Berlin, Germany

来源：

ADVANCES IN COMPUTATIONAL MATHEMATICS | 2019年 / 45卷 / 5-6期

关键词：

Machine learning; Uncertainty quantification; Partial differential equations; Statistical learning; Tree tensor networks; STOCHASTIC COLLOCATION METHOD; UNIFORM-CONVERGENCE; APPROXIMATION;

D O I：

10.1007/s10444-019-09723-8

中图分类号：

O29 [应用数学];

学科分类号：

070104 ;

摘要：

A statistical learning approach for high-dimensional parametric PDEs related to uncertainty quantification is derived. The method is based on the minimization of an empirical risk on a selected model class, and it is shown to be applicable to a broad range of problems. A general unified convergence analysis is derived, which takes into account the approximation and the statistical errors. By this, a combination of theoretical results from numerical analysis and statistics is obtained. Numerical experiments illustrate the performance of the method with the model class of hierarchical tensors.

引用

页码：2503 / 2532

页数：30

共 50 条

[1] Variational Monte Carlo—bridging concepts of machine learning and high-dimensional partial differential equations [J].

Martin Eigel ;

Reinhold Schneider ;

Philipp Trunschke ;

Sebastian Wolf .

Advances in Computational Mathematics, 2019, 45 :2503-2532

[2] Variational Monte Carlo approach to partial differential equations with neural networks [J].

Reh, Moritz ;

Gaerttner, Martin .

MACHINE LEARNING-SCIENCE AND TECHNOLOGY, 2022, 3 (04)

[3] Solving high-dimensional partial differential equations using deep learning [J].

Han, Jiequn ;

Jentzen, Arnulf ;

Weinan, E. .

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2018, 115 (34) :8505-8510

[4] SelectNet: Self-paced learning for high-dimensional partial differential equations [J].

Gu, Yiqi ;

Yang, Haizhao ;

Zhou, Chao .

JOURNAL OF COMPUTATIONAL PHYSICS, 2021, 441

[5] Monte Carlo fPINNs: Deep learning method for forward and inverse problems involving high dimensional fractional partial differential equations [J].

Guo, Ling ;

Wu, Hao ;

Yu, Xiaochen ;

Zhou, Tao .

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2022, 400

[6] A least-squares approximation of partial differential equations with high-dimensional random inputs [J].

Doostan, Alireza ;

Iaccarino, Gianluca .

JOURNAL OF COMPUTATIONAL PHYSICS, 2009, 228 (12) :4332-4345

[7] Reduced basis ANOVA methods for partial differential equations with high-dimensional random inputs [J].

Liao, Qifeng ;

Lin, Guang .

JOURNAL OF COMPUTATIONAL PHYSICS, 2016, 317 :148-164

[8] Numerically Solving Parametric Families of High-Dimensional Kolmogorov Partial Differential Equations via Deep Learning [J].

Berner, Julius ;

Dablander, Markus ;

Grohs, Philipp .

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33

[9] MULTILEVEL MONTE CARLO ON A HIGH-DIMENSIONAL PARAMETER SPACE FOR TRANSMISSION PROBLEMS WITH GEOMETRIC UNCERTAINTIES [J].

Scarabosio, Laura .

INTERNATIONAL JOURNAL FOR UNCERTAINTY QUANTIFICATION, 2019, 9 (06) :515-541

[10] An Adaptive ANOVA Stochastic Galerkin Method for Partial Differential Equations with High-dimensional Random Inputs [J].

Wang, Guanjie ;

Sahu, Smita ;

Liao, Qifeng .

JOURNAL OF SCIENTIFIC COMPUTING, 2024, 98 (01)

← 1 2 3 4 5 →