VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.

401-3650-23L 4 Credits MSC D-MATH

Numerical Analysis Seminar: Deep Neural Network Methods for PDEs

Lecturers & Examiners: Prof. Dr. Christoph Schwab
Number of participants limited to 7. Participation by consent of instructor. Physical presence required for participation.
VVZ CR n/a

Last Updated: 2026-02-05 16:37:22

Abstract

The Seminar will review recent research papers and research results on the mathematical analysis (convergence rates, error vs. work, expression rate bounds, etc.) of deep learning based numerical methods for partial differential equations (PDEs).Particular attention is on high-dimensional PDEs as arise in financial modelling, physics, etc.

General Information

Language
English
Levels
MSC

Examination

Type
ungraded semester performance
Passing grade will requirea) 1hr oral presentation with Q/A from the seminar group andb) typed seminar report (``Ausarbeitung'') of several key aspects of the paper under review.

Registration & Places

Limited places (Special selection)
Signup Start
01.01.2024
Signup End
10.02.2024
Priority: Registration for the course unit is only possible for the primary target group

Course Components

Type Title Time & Place Hours
seminar Numerical Analysis Seminar: Deep Neural Network Methods for PDEs
Permission from lecturers required for all students.
  • 28.02 Date 12:15-14:00 (HG D 5.3)
  • 27.03 Date 12:15-14:00 (HG D 5.3)
  • 16.05 Date 10:15-12:00 (HG F 26.3)
  • 16.05 Date 13:15-16:00 (HG F 26.3)
  • 17.05 Date 10:15-13:00 (HG F 26.3)
  • 21.05 Date 08:15-13:00 (HG F 26.3)
2 h weekly

Offered In

  • Mathematics Master
    • Seminars and Semester Papers
      • Seminars (NOTICE: The number of seminar places is limited, and the special selection procedure should help to allocate the places not primarily according to the registration time. Everybody is waitlisted first when he/she tries to register for a seminar in myStudies. Moreover: Only one mathematics seminar can be chosen per semester. In case you need to attend 2 seminars in this semester, please take contact with the Study Administration (email: ). Notice also the course unit 401-0002-99L Generic Seminar - Second Priority / Third Priority.)