WIAS invites applications for a
PhD student position (f/m/d) in
robust machine learning and data-driven optimization
(Ref. 21/15)

in the Weierstrass Group “Data‐driven Optimization and Control” (Head: Dr. Jia-Jie Zhu) starting as soon as possible.
Robustness plays an increasingly important role in machine learning and optimization. For example, learners and optimization solutions can become fragile once the test environments differ from training. We are looking for candidates passionate about researching robustness in data-driven optimization and machine learning, broadly defined as, e.g., distributional robustness/adversarial robustness/generalization/interfacing distributional robustness and causality/robust optimization/robustness in RL and control.
We invite candidates with a degree (master’s level) in mathematics, computer science, or control theory, and backgrounds in mathematical optimization and/or machine learning theory and/or control theory. Candidates with strong applied or industrial experiences will also be considered. Those qualifications are demonstrated by high-quality technical reports or publications in credible venues and/or completed industrial projects and codebases.
Examples of the background include (but not limited to):
· Optimization: (distributionally) robust optimization/stochastic programming, numerical optimization, mixed-integer programming, semi-definite/semi-infinite optimization
· Applied math: numerical/functional analysis, approximation theory, differential equation
· Control: optimal control, robust control, MPC, data-driven control, dynamics learning
· Machine learning: adversarial robustness, generative models, learning theory, RL, kernel methods
What we offer:
· Close mentorship: the Ph.D. candidate will receive responsible and careful mentorship. We emphasize fostering a healthy mentor-student relationship.
· WIAS Berlin is a premier research institution known for its strength in optimization, optimal control, dynamical systems, and applied mathematics in general. It has hosted the flagship conferences in mathematical optimization such as ICCOPT 2019. We also envision collaborations with our collaborators within WIAS as well as external top institutions such as the Max Planck Institute for Intelligent Systems, Tübingen.
· A certified (Audit berufundfamilie) family-friendly work environment.
· There is no teaching duty envisioned.
· Berlin is one of the most culture-rich and diverse international cities in the world. It offers endless opportunities to enjoy life outside work, while being very affordable compared to other major cities. Neither the job nor living in Berlin requires German language (although WIAS offers free German courses). We highly welcome international applications. Scientifically, Berlin offers a rich landscape with numerous opportunities for research, as well as job prospects in academia and industry.

Please direct queries to Dr. Jia-Jie Zhu (zhu@wias-berlin.de), further information on his work is also available at https://jj-zhu.github.io/.
The appointment is for 36 months. The reduced work schedule is 29,25 hours per week and the salary is according to the German TVoeD scale.

See here for more information: https://short.sg/j/11539907