Ethan Jacob Leeman — accepted AI-conference papers

2025

Balls-and-Bins Sampling for DP-SGD

Lynn Chua, Badih Ghazi, Charlie Harrison, Pritish Kamath, Ravi Kumar, Ethan Jacob Leeman +3

AISTATS 2025oral

We introduce the _Balls-and-Bins_ sampling for differentially private (DP) optimization methods such as DP-SGD. While it has been common practice to use some form of shuffling in DP-SGD implementations, privacy accounting algorithms have typically assumed that Poisson subsampling is used instead. Re…

Cited by 0 Source ↗Scholar ↗

2023

Optimal Unbiased Randomizers for Regression with Label Differential Privacy

Ashwinkumar Badanidiyuru, Badih Ghazi, Pritish Kamath, Ravi Kumar, Ethan Jacob Leeman, Pasin Manurangsi +2

NeurIPS 2023poster

We propose a new family of label randomizers for training _regression_ models under the constraint of label differential privacy (DP). In particular, we leverage the trade-offs between bias and variance to construct better label randomizers depending on a privately estimated prior distribution over…

Cited by 4 Source ↗PDF ↗Scholar ↗