University of Cambridge and MPI for Intelligent Systems, Tübingen
SWS Colloquium
Niki Kilbertus is a final-year PhD student in the Cambridge-Tübingen program co-supervised by Bernhard Schölkopf and Carl Rasmussen. He is primarily interested in building socially beneficial, robust, and theoretically substantiated machine learning systems. Prior, Niki studied physics and mathematics at the University of Regensburg with research visits at Harvard and Stanford.
AG 1, AG 2, AG 3, INET, AG 4, AG 5, SWS, RG1, MMCI
Machine learning increasingly supports consequential decisions in health, lending, criminal justice or employment that affect the wellbeing of individual members or entire groups of our society. Such applications raise concerns about fairness, privacy violations and the long-term consequences of automated decisions in a social context. After a brief introduction to fairness in machine learning, I will highlight concrete settings with specific fairness or privacy ramifications and outline approaches to address them. I will conclude by embedding these examples into a broader context of socioalgorithmic systems and the complex interactions therein.