[Opt-Net] PhD student position (f/m/d) (f/m/d) on machine learning for inverse problems , with continuous normalizing flows and mean field games (Ref. 22/17) at WIAS, Berlin, Germany

[Heike Sill]

WIAS invites applications for a

PhD student position (f/m/d)

(Ref. 22/17)

in the Research Group

“Nonlinear Optimization and Inverse Problems”

(Head: Prof. Dr. D. Hömberg) starting at the earliest possible date.

The position is tied to the project

“Machine Learning for Inverse Problems

with continuous normalizing flows and mean field games”

PI: PD Dr. Martin Eigel). The goal of the project is the development and 
analysis of Neural Networks for invertible measure transport such as 
normalizing flows. Connections to optimal transport, optimal control, 
mean field games and stochastic differential equations will be examined. 
Moreover, low-rank tensor formats will be used in a hybrid method. In 
collaboration with the PTB, the developed methods will be applied to 
inverse problems for geometry parameters the quality control of 
semiconductor manufacturing.

We are looking for candidates with a solid background in applied 
mathematics, theoretical chemistry, theoretical physics, or electrical 
engineering. They are expected to be familiar with some of the topics 
numerical analysis (for differential equations), quantification of 
uncertainty, statistical learning theory, high-dimensional 
approximations, stochastic analysis. Applicants are also expected to 
have experience with at least one of the popular Python frameworks for 
machine learning. Previous experience in continuum mechanics, 
thermodynamics, homogenization theory, software engineering, or machine 
learning are beneficial.

A completed scientific university degree (master’s degree) in 
mathematics or a closely related field is required as well as 
demonstrable programming experience preferably in python and good 
communication skills in English. An applied mathematical education (in 
particular numerical analysis, functional analysis or stochastic 
analysis) is required for a successful application. Moreover, experience 
in the implementation of machine learning models and numerical 
algorithms is beneficial.

Queries about the project can be directed to Dr. M. Eigel 
(Martin.Eigel at wias-berlin.de <mailto:eigel at wias-berlin.de?subject=22-03>).

The appointment is limited for three years until 31.03.2025. The reduced 
work schedule is 29,25 hours per week, and the salary is according to 
the German TVoeD Bund scale.

The Institute aims to increase the proportion of women in this field, so 
applications from women are particularly welcome. Among equally 
qualified applicants, disabled candidates will be given preference.

Please upload your complete application documents (motivation letter, 
detailed CV, certificates, list of MSc courses and grades, copy of the 
master‘s thesis or draft, two recommendation contacts) via our applicant 
portal <https://short.sg/j/17430658> as soon as possible but not later 
than May 15, 2022 using the button "Apply online 
<https://short.sg/a/17430658>".

We are looking forward to your application!

See here for more information:https://short.sg/j/17430658 
<https://short.sg/j/17430658>

-- 
Administration
Weierstrass Institute for Applied Analysis and Stochastics
Mohrenstrasse 39
10117 Berlin, Germany
Phone: +49 (0)30  20372 557
Fax: +49 (0)30 20372 329
URL:http://www.wias-berlin.de/~sill/?lang=1
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.zib.de/pipermail/opt-net/attachments/20220408/0f7d1874/attachment.html>