Showing stat.MLShow all
2 papers · 1 filter
stat.ML2025
Some Robustness Properties of Label Cleaning
Chen Cheng, John Duchi
We demonstrate that learning procedures that rely on aggregated labels, e.g., label information distilled from noisy responses, enjoy robustness properties impossible without data…
stat.ML2024
Resampling methods for private statistical inference
Karan Chadha, John Duchi, Rohith Kuditipudi
We consider the task of constructing confidence intervals with differential privacy. We propose two private variants of the non-parametric bootstrap, which privately compute the me…