#machine learning
Jan 2026
DP-λCGD: Efficient Noise Correlation for Differentially Private Model Training
This work proposes a new algorithm for correlated-noise private training that correlates noise only with the immediately preceding iteration and cancels a tunable portion of it and shows that the computational overhead is minimal and improved accuracy over DP-SGD is demonstrated.
Nikita P. Kalinin, Ryan McKenna, Rasmus Pagh et al.
· arXiv.org · 3 citations