Ryan McKenna

Back to Square Roots: An Optimal Bound on the Matrix Factorization Error for Multi-Epoch Differentially Private SGD

Differentially Private Conditional Text Generation with RL-Boosted Control

Scaling up the Banded Matrix Factorization Mechanism for Large Scale Differentially Private ML

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

Scaling Laws for Differentially Private Language Models