![](https://media.springernature.com/w290h158/springer-static/image/art%3A10.1007%2Fs40687-022-00327-1/MediaObjects/40687_2022_327_Figa_HTML.png)
Collection
Mathematical Theory of Machine Learning and Applications
- Submission status
- Closed
In the past decade, deep learning as a branch of machine learning has influenced scientific computing in a fundamental way. This computational breakthrough presents tremendous opportunities and needs for new perspectives on computational mathematics and related emerging fields, such as approximation theory, operator estimation, numerical PDEs, inverse problems, data-driven modeling of dynamical systems, unsupervised and semi-supervised learnings. This special issue features high-quality original research relating to the theoretical and computational developments in these topics.
Editors
-
John Harlim
Institute for Computational and Data Sciences, The Pennsylvania State University
-
Thomas Hou
California Institute of Technology
-
Jinchao Xu
The Pennsylvania State University
Articles (5 in this collection)
-
-
Learning generative neural networks with physics knowledge
Authors
- Kailai Xu
- Weiqiang Zhu
- Eric Darve
- Content type: Research
- Published: 17 May 2022
- Article: 33
-
Computational graph completion
Authors
- Houman Owhadi
- Content type: Research
- Published: 18 April 2022
- Article: 27
-
On Lyapunov functions and particle methods for regularized minimax problems
Authors
- Lexing Ying
- Content type: Research
- Published: 03 March 2022
- Article: 18
-
Learning quantized neural nets by coarse gradient method for nonlinear classification
Authors
- Ziang Long
- Penghang Yin
- Jack Xin
- Content type: Research
- Open Access
- Published: 31 July 2021
- Article: 48