A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2023; you can also visit the original URL.
The file type is application/pdf
.
Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams
[article]
2023
arXiv
pre-print
Motivated by recent applications requiring differential privacy over adaptive streams, we investigate the question of optimal instantiations of the matrix mechanism in this setting. We prove fundamental theoretical results on the applicability of matrix factorizations to adaptive streams, and provide a parameter-free fixed-point algorithm for computing optimal factorizations. We instantiate this framework with respect to concrete matrices which arise naturally in machine learning, and train
arXiv:2202.08312v3
fatcat:rlprkyjg25ecvbegkup34esnbu