3 papers
cs.CY2026
Auditing a Dutch Public Sector Risk Profiling Algorithm Using an Unsupervised Bias Detection Tool
Floris Holstege, Mackenzie Jorgensen, Kirtan Padh +4
Algorithms are increasingly used to automate or aid human decisions, yet recent research shows that these algorithms may exhibit bias across legally protected demographic groups. H…
cs.LG2025
Preserving Task-Relevant Information Under Linear Concept Removal
Floris Holstege, Shauli Ravfogel, Bram Wouters
Modern neural networks often encode unwanted concepts alongside task-relevant information, leading to fairness and interpretability concerns. Existing post-hoc approaches can remov…
stat.ML2025
Optimizing importance weighting in the presence of sub-population shifts
Floris Holstege, Bram Wouters, Noud van Giersbergen +1
A distribution shift between the training and test data can severely harm performance of machine learning models. Importance weighting addresses this issue by assigning different w…