activity
20242026
most citedBack to Square Roots: An Optimal Bound on the Matrix Factorization Error for Multi-Epoch Differentially Private SGD

1 citations · 1 across the 2 of their papers we have counts for

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2026

DP-λCGD: Efficient Noise Correlation for Differentially Private Model Training

Nikita P. Kalinin, Ryan McKenna, Rasmus Pagh +1

Differentially private stochastic gradient descent (DP-SGD) is the gold standard for training machine learning models with formal differential privacy guarantees. Several recent ex…

cs.LG2024

Scaling up the Banded Matrix Factorization Mechanism for Differentially Private ML

Ryan McKenna

Correlated noise mechanisms such as DP Matrix Factorization (DP-MF) have proven to be effective alternatives to DP-SGD in large-epsilon few-epoch training regimes. Significant work…