Learning for Combinatorial Optimization"
Please share with anyone looking for a position!
Be a part of the newly-funded DFG project "Automatically learning to
solve optimization problems with deep reinforcement learning: The quest
for feasibility" with André Hottung and me at Bielefeld University.
What we offer
- A 3 year, 100% "E13" PhD position (extremely well funded, and includes
travel money for conferences, PhD schools, etc.)
- Access to two different GPU clusters with 128 Nvidia A100 and 224
Nvidia V100 GPUs, respectively. (not to mention over 126,000 CPU cores...)
- Years of experience applying DRL to CO problems
- Structured PhD program (BiGSEM) providing interaction with a large
group of PhD students researching topics in operations research,
management, economics and data science.
- My research group's "default" language is English, no German language
knowledge is required for the position and you will feel right at home here.
Why Bielefeld?
- Live right next to the famed Teutoburger forest
- Low living cost relative to other German cities (use your salary for
something fun, rather than paying for a closet-sized apartment in Munich)
- Has a castle right in the middle of the city
- It actually exists. (if this makes no sense to you... well don't
worry, the "joke" will be explained to you a hundred times by
non-Bielefelders)
How to apply
See: https://uni-bielefeld.hr4you.org/job/view/2532/
When applying, please take advantage of the cover letter to highlight
your experience using deep learning techniques and, if you have OR
experience, what kind of problems you have tackled.
If you have any questions, please contact me at
kevin.tierney@uni-bielefeld.de
Kevin
--
Prof. Dr. Kevin Tierney
Professor for Decision and Operation Technologies
Faculty of Business Administration and Economics
Bielefeld University
Tel: +49 (0)521 106-3940
Room: U9-121
**********************************************************
*
* 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
