Hein (Machine Learning Group) and Simon Setzer (Mathematical Image
Analysis Group) at Saarland University, Saarbrücken. The main focus of
the project is to develop new data analysis methods based on nonlinear
eigenproblems. Nonlinear eigenproblems have recently been introduced
in the machine learning community and offer much richer modeling
flexibility compared to linear eigenproblems. This allows the
development of robust and sparsity enforcing methods for
dimensionality reduction or the tight relaxation of certain
combinatorial problems (graph partitioning) as nonlinear
eigenproblems. In this project, we develop new optimization techniques
to compute nonlinear eigenvectors efficiently and employ nonlinear
eigenproblems to solve a variety of problems in data analysis.
Saarbrücken is located in the south-western part of Germany, close to
the French border. It is home of one of the leading computer science
departments and affiliated with several top public and private
research centers. The working language is English.
We are inviting applications of candidates with the following background:
- a master/diploma in mathematics, computer science or physics,
- strong analytical skills,
- programming skills (C/Matlab),
- knowledge in at least one of the following fields: convex
optimization, functional analysis, machine learning/statistics.
Postdocs should in addition have a strong publication record in
machine learning/statistics and/or optimization.
The position is immediately available. Applications will be considered
until the position is filled. Candidates must already be authorized to
work in Germany. Please send your application per email to:
Prof. Dr. Matthias Hein
Machine Learning Group
E-mail: hein@cs.uni-sb.de
and
Dr. Simon Setzer
Mathematical Image Analysis Group
E-mail: setzer@mia.uni-saarland.de
Department of Mathematics and Computer Science, Campus E 1.1
66041 Saarbrücken, Germany
**********************************************************
*
* Contributions to be spread via DMANET are submitted to
*
* DMANET@zpr.uni-koeln.de
*
* Replies to a message carried on DMANET should NOT be
* addressed to DMANET but to the original sender. The
* original sender, however, is invited to prepare an
* update of the replies received and to communicate it
* via DMANET.
*
* DISCRETE MATHEMATICS AND ALGORITHMS NETWORK (DMANET)
* http://www.zaik.uni-koeln.de/AFS/publications/dmanet/
*
**********************************************************
Posts
