I am Oliver Hennhöfer, a research staff member at Hochschule Karlsruhe in the Intelligent Systems Research Group. My work sits at the intersection of statistics and machine learning, with a focus on anomaly detection, conformal inference, uncertainty quantification, and online false discovery rate control.
I am interested in machine learning systems that remain useful when data are scarce, noisy, non-stationary, or arrive sequentially. Recent work studies resampling-based conformal anomaly detectors and weighted conformal methods for low-data regimes and distribution shift.
I also build research software. nonconform turns anomaly scores into conformal p-values and FDR-controlled decisions, while online-fdr implements sequential multiple-testing procedures for settings where decisions must be made as data arrives.
Beyond research, I care about clear technical communication and approachable teaching material, including interdisciplinary ways to make AI and computer science more accessible.
Links
Contact
The best way to reach me is via email at oliver.hennhoefer@mail.de.