A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations

Thumbnail
Metadata only
Author
Hutzenthaler, Martin
Jentzen, Arnulf
Kruse, Thomas
Nguyen, Tuan A.
Show all
Date
2019-02
Type
    Report
Publication status
published
External links
https://math.ethz.ch/sam/research/reports.html?id=814
Journal / series
SAM Research Report
Volume
2019-10
Publisher
Seminar for Applied Mathematics, ETH Zurich
Subject
curse of dimensionality; high-dimensional PDEs; deep neural networks; information based complexity; tractability of multivariate problems; multilevel Picard approximations
Organisational unit
03951 - Jentzen, Arnulf (ehemalig) / Jentzen, Arnulf (former)  
More
Show all metadata
ETH Bibliography
yes
Altmetrics