Below is a list of possible thesis projects within the FMLS group. These should be considered starting points only. An essential part of doing a thesis is the formulation and refinement of the problem itself.
- Bachelor/Master (strong focus on Math): What does predictor learn when doing ``robust learning''? - Property Elicitation for Imprecise Probability (Rabanus) PS: more detailed abstract on demand per mail
- Master (strong focus on Math): Algebraic Structure of Elicitable Properties (Rabanus) PS: more detailed abstract on demand per mail
- Master: Intersectional Fairness through the Lens of Collectives and Hypergraphs (Rabanus)
- Master: Calibrated Predictions for Performative Equilibria on Aggregates (Rabanus)
- Master: Surveying and expanding existing understanding of robust learning models from a statistical point of view (e.g., unbiasedness/consistency of risk estimators) (Laura and Nan)
- Master: Learning under general corruption -- definition and theoretical analysis (Laura)
- Bachelor/Master: Consequences of Markovian corruption on learning -- empirical study, but it can also delve into the theoretical part depending on the student’s interest (Laura and Nan)
Don't hesitate to ask for an informal meet-up with somebody of our group to get a bit more information on the topics (see the names in brackets).