3 papers
stat.ME2025
Gaussian Rank Verification
Jeremy Goldwasser, Will Fithian, Giles Hooker
Statistical experiments often seek to identify random variables with the largest population means. This inferential task, known as rank verification, has been well-studied on Gauss…
stat.ME2025
Controlling the false discovery rate under a non-parametric graphical dependence model
Drew T. Nguyen, William Fithian
We propose sufficient conditions and computationally efficient procedures for false discovery rate control in multiple testing when the -values are related by a known \emph{depe…
cs.LG2025
Forecasting Rare Language Model Behaviors
Erik Jones, Meg Tong, Jesse Mu +7
Standard language model evaluations can fail to capture risks that emerge only at deployment scale. For example, a model may produce safe responses during a small-scale beta test,…