Differentially Private Coordinate Descent for Composite Empirical Risk Minimization. (arXiv:2110.11688v3 [cs.LG] UPDATED)

Machine learning models can leak information about the data used to train
them. To mitigate this issue, Differentially Private (DP) variants of
optimization algorithms like Stochastic Gradient Descent (DP-SGD) have been
designed to trade-off utility for privacy in Empirical Risk Minimization (ERM)
problems. In this paper, we propose Differentially Private proximal Coordinate
Descent (DP-CD), a new method to solve composite DP-ERM problems. We derive
utility guarantees through a novel theoretical analysis of inexact coordinate
descent. Our results show that, thanks …

minimization risk