Kilbertus Research Group — Trustworthy Machine Learning
Welcome to the Kilbertus Research Group at the Technical University of Munich (TUM). We develop machine learning methods that are fair, transparent, and privacy-preserving, with a strong foundation in causal inference and statistics.
Our work sits at the intersection of:
- Causal Inference — understanding cause-and-effect relationships from data
- Algorithmic Fairness — ensuring automated decisions are equitable and non-discriminatory
- Privacy-Preserving ML — enabling collaborative learning without compromising data privacy
- Uncertainty Quantification — reasoning about uncertainty in predictions and causal effects
We are part of the TUM School of Computation, Information and Technology and affiliated with Helmholtz AI.
Research Highlights
- Causal Fairness in Machine Learning — Formal causal frameworks for fairness in automated decision-making
- Privacy-Preserving Federated Learning — Collaborative learning with differential privacy guarantees
- Uncertainty Quantification with Bayesian Causal Models — Rigorous uncertainty estimates for causal effects
Latest News
See our News page for the latest updates, or browse our Publications for recent papers.
Joining the Group
We welcome applications from motivated students and researchers. See our Join Us page for current open positions and how to apply.