The group "Mathematical Data Science" represents the area of data science, particularly in relation to different aspects of applied mathematics.

Its research is motivated by interdisciplinary applications and ranges from theory over algorithm development to the solution of real-world problems.

A current focus lies on the development of mathematical theory for deep learning algorithms with the goal of extending the scope of applications of deep learning towards problems that require some degree of “understanding” of the data’s inherent characteristics and the structure of the domain they come from. As a concrete example we develop and rigorously analyze deep learning methods for the numerical solution of high dimensional problems arising in engineering and finance (for example the pricing of financial derivatives) that cannot be efficiently solved using standard methods.