Arun Ganesh

Near-Exact Privacy Amplification for Matrix Mechanisms

It's My Data Too: Private ML for Datasets with Multi-User Training Examples

The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD

Privacy Amplification for Matrix Mechanisms

Correlated Noise Provably Beats Independent Noise for Differentially Private Learning

The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD