My research is on the mathematical foundations of artificial intelligence and machine learning, where I focus on learning in networks of interacting agents. I approach this question from the perspectives of evolutionary game theory, dynamic systems, and Markov chains, in order to obtain convergence and optimality proofs for learning algorithms.
It is motivated by the question of how animal brains learn through neural plasticity and how this could inform the training of artificial neural networks. In particular, I am interested in the mathematical (and computational) properties that enable learning.
Interests. Evolutionary game theory, stability analysis of dynamic systems, reinforcement learning, Markov decision processes, Markov chains, and optimization; more recently, also probabilistic graphical models.
My further interests concern the fundamentals of mathematics (mathematical logic, formal systems and languages, computability), the philosophy of mathematics, the philosophy of mind and of language, and economics.
Mathematics, PhD, City, University of London. 2021.
Mathematics, Diplom (MSc+BSc equiv.), University of Konstanz, Germany. 2017. Concentration: Optimization, Functional Analysis, Logic and Model theory. (Minor: Philosophy.)
Economics, BA, University of St. Gallen, Switzerland. 2012. Concentration: Microeconomics, Equilibrium Theory, Quantitative Methods. (Minor: International Affairs.)