Research Interest:
Optimization, especially Convex Optimization and in general optimization for Machine Learning
Statistics, especially Estimation Theory and Bayesian Statistics
Bayesian Optimization
Information Theory
Statistical and Probabilistic Machine Learning
Brief Bio:
Michael Sucker received a B.Sc. in Medical Engineering in 2016 from the Furtwangen University
(HFU), Tuttlingen. After a short stay abroad in Spain, he started his studies in mathematics with
applications in computer science at the University of Heidelberg in October 2016. There, his main
interest where in the areas of stochastics, numerics and machine learning. He received his B.Sc. in
mathematics in March 2020, where his thesis dealt with topics from statistical learning theory. In
April 2020, Michael continued to study mathematics at the University of Tübingen, where he started
his masters degree. Now, the main focus was on the areas of stochastics and machine learning,
especially their combination in statistical and probabilistic machine learning. Alongside his studies, he
was a working student in the field of autonomous driving.
Michael started his master thesis under the supervision of Prof. Ochs in October 2021.
The topic deals with the acceleration of firstorder optimization algorithms for specialized classes
of optimization problems. After this thesis, he will join the Mathematical Optimization Group as a PhD
student in April 2022. His research interests lie in the fields of mathematics that are adjacent to
machine learning, especially stochastics, optimization and efficient algorithm design.
