按年被提到
20172020 · 1 次2026
机器学习与深度学习›科学机器学习·arXiv:1708.07469 · q-fin.MF

DGM: A deep learning algorithm for solving partial differential equations

Justin Sirignano, Konstantinos Spiliopoulos · 2017
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2020-10-21 · 最近 2021-03-28发表于 Journal of Computational Physics
2不同的人
2活跃月份
2讨论串
2,216被引(OpenAlex)
arXiv 摘要(候选层不写导读)

High-dimensional PDEs have been a longstanding computational challenge. We propose to solve high-dimensional PDEs by approximating the solution with a deep neural network which is trained to satisfy the differential operator, initial condition, and boundary conditions. Our algorithm is meshfree, which is key since meshes become infeasible in higher dimensions. Instead of forming a mesh, the neural network is trained on batches of randomly sampled time and space points. The algorithm is tested on a class of high-dimensional free boundary PDEs, which we are able to accurately solve in up to $200$ dimensions. The algorithm is also tested on a high-dimensional Hamilton-Jacobi-Bellman PDE and Burgers' equation. The deep learning algorithm approximates the general solution to the Burgers' equation for a continuum of different boundary conditions and physical conditions (which can be viewed as a high-dimensional space). We call the algorithm a "Deep Galerkin Method (DGM)" since it is similar in spirit to Galerkin methods, with the solution approximated by a neural network instead of a linear combination of basis functions. In addition, we prove a theorem regarding the approximation power of neural networks for a class of quasilinear parabolic PDEs.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论syntaxing · 2020-10

“Fun article to read but using incompressible flow as an assumption is extremely dangerous. The main effect of the assumption is that density does not change which is not the case for airfoils, particularly near the wake which usually ends up as P_0 (ambient pressure). It would be even more awesome if the author left NS in it's standard form and add the ne…”

Optimizing a Wing原评论 ↗
评论activatedgeek · 2021-03

“And, guess what? Since, the Galerkin approximation requires one to choose a basis that is appropriate to the problem at hand, we now have a deep learning solution too (since neural network learning is essentially equivalent to learning an adaptive basis). It is called the Deep Galerkin Method [1]. In a nutshell, the method directly minimizes the L2 error…”

Galerkin Approximation原评论 ↗