2 papers
stat.ML2026
Finding Most Influential Sets
Lucas D. Konrad, Nikolas Kuschnig
Identifying most influential sets (MIS) - size- subsets whose removal maximally changes a target estimand - is typically infeasible because it requires searching over $\binom{n}…
stat.ML2026
Testing Most Influential Sets
Lucas D. Konrad, Nikolas Kuschnig
Small influential data subsets can dramatically impact model conclusions, with a few data points overturning key findings. While recent work identifies these most influential sets,…