Fields of Interest
We consider and analyze machine learning problems from the perspective of complexity theory. We try to determine the information or computational complexity of learning problems, and to design efficient learning algorithms. Furthermore, we investigate combinatorial optimization problems and explore the possibility of designing efficient approximation algorithms. We have a general interest in finding new programming methods and in inventing new data structures. We are furthermore interested in any results that shed more light on the famous P-NP problem.
Computational geometry. We study the design and analysis of efficient algorithms and data structures for geometric problems. In particular, we are interested in shape matching, that is developing algorithms for determing the similarity of geometric shapes. Furthermore, we are interested in applications of computational geometry to geographic data, in particular to movement data.
"Cryptography in Ubiquitious Computing: Privacy-preserving Learning"
Graduiertenkolleg (GRK 1817) funded by the German Research Corporation (DFG)
"Privacy-Preserving Learning" is among the projects of GRK 1817. In this project, we are concerned with techniques that allow to perform statistical analysis of data in a privacy-preserving fashion. In particular, we investigate how well the objectives of statistical learning can be pursued subject to the constraint of achieving epsilon-differential privacy. We further more study variations in the notion of privacy-preservation and analyze how they relate to each other.